Clinicaltrials Gov Tools#

Configuration File: clinicaltrials_gov_tools.json Tool Type: Local Tools Count: 16

This page contains all tools defined in the clinicaltrials_gov_tools.json configuration file.

Available Tools#

ClinicalTrials_get_database_stats (Type: ClinicalTrialsTool)#

Get aggregate statistics about the ClinicalTrials.gov database, including total number of registe…

ClinicalTrials_get_database_stats tool specification

Tool Information:

  • Name: ClinicalTrials_get_database_stats

  • Type: ClinicalTrialsTool

  • Description: Get aggregate statistics about the ClinicalTrials.gov database, including total number of registered studies and size distribution. Returns database-wide counts and file size metrics.

Parameters:

No parameters required.

Example Usage:

query = {
    "name": "ClinicalTrials_get_database_stats",
    "arguments": {
    }
}
result = tu.run(query)

ClinicalTrials_get_field_values (Type: ClinicalTrialsTool)#

Get the registry-wide value distribution for one ClinicalTrials.gov field: each distinct value wi…

ClinicalTrials_get_field_values tool specification

Tool Information:

  • Name: ClinicalTrials_get_field_values

  • Type: ClinicalTrialsTool

  • Description: Get the registry-wide value distribution for one ClinicalTrials.gov field: each distinct value with the number of studies recording it. Use to see what status, phase, or study type options exist. Example: ‘Phase’ returns counts for PHASE1, PHASE2, PHASE3, etc. IMPORTANT for any share or percentage: the rows are NOT a partition of the registry. Studies that record no value for the field are excluded from the rows entirely (for ‘Phase’, 141,728 of 597,913), and where the field is multi-valued a study recording several values is counted in several rows (for ‘Phase’, 24,529 studies), so the rows sum to neither the registry total nor a subset of it. Never use the sum of the rows as a denominator; use ‘total_studies_in_registry’ for a share of all studies or ‘studies_with_value’ for a share of those recording the field, and read ‘coverage_note’ before quoting any percentage.

Parameters:

  • field (string) (required) Field name to get value counts for. Common fields: ‘OverallStatus’ (trial status), ‘Phase’ (trial phase), ‘StudyType’ (Interventional/Observational), ‘LeadSponsorClass’ (industry/NIH/other), ‘InterventionType’ (drug/device/biological).

  • query_cond ([‘string’, ‘null’]) (optional) NOT SUPPORTED - passing this returns an error. ClinicalTrials.gov’s field-value statistics endpoint counts values across the whole registry and accepts no condition, status or phase filter (it rejects any such parameter with HTTP 400). For counts restricted to a condition, use ClinicalTrials_search_studies with query_cond and tally the per-study ‘status’, ‘phases’, ‘study_type’ or ‘sponsor’ fields it returns.

  • page_size (integer) (optional) Maximum number of value rows to return, highest study count first (default 50, minimum 1). Truncation is reported: when this cuts the list, ‘truncated’ is true and ‘unique_values_count’ still gives the true number of distinct values. The counts in ‘missing_studies_count’, ‘studies_with_value’ and ‘coverage_note’ always describe the whole facet, never just the returned rows.

Example Usage:

query = {
    "name": "ClinicalTrials_get_field_values",
    "arguments": {
        "field": "example_value"
    }
}
result = tu.run(query)

ClinicalTrials_get_study (Type: ClinicalTrialsTool)#

Get full details for a specific clinical trial by NCT ID from ClinicalTrials.gov. Returns compreh…

ClinicalTrials_get_study tool specification

Tool Information:

  • Name: ClinicalTrials_get_study

  • Type: ClinicalTrialsTool

  • Description: Get full details for a specific clinical trial by NCT ID from ClinicalTrials.gov. Returns comprehensive protocol including title, objectives, eligibility criteria, interventions, outcome measures, contacts, and results summary. Example: NCT04280705 returns the ACTT remdesivir COVID-19 trial with all details.

Parameters:

  • nct_id (string) (required) NCT (National Clinical Trial) identifier (e.g., ‘NCT04280705’, ‘NCT02142712’). Obtain from ClinicalTrials_search_studies.

Example Usage:

query = {
    "name": "ClinicalTrials_get_study",
    "arguments": {
        "nct_id": "example_value"
    }
}
result = tu.run(query)

ClinicalTrials_search_by_intervention (Type: ClinicalTrialsTool)#

Search ClinicalTrials.gov for all clinical trials testing a specific drug, biologic, device, or o…

ClinicalTrials_search_by_intervention tool specification

Tool Information:

  • Name: ClinicalTrials_search_by_intervention

  • Type: ClinicalTrialsTool

  • Description: Search ClinicalTrials.gov for all clinical trials testing a specific drug, biologic, device, or other intervention. Returns trial IDs, titles, phases, status, and conditions being studied. Ideal for finding all trials for a given drug (e.g., ‘nivolumab’) across all disease indications. Query rewriting: multi-word intervention/condition/sponsor values are sent to ClinicalTrials.gov as an EXACT PHRASE, and intervention/sponsor values are further restricted to specific registry fields, so a phrase no registrant recorded verbatim can match 0 studies even when many trials mention it. The query actually executed is always returned in executed_query (with per-parameter detail in query_rewrites); when a rewritten query matches nothing, relaxed_match_check reports how many studies your original wording would have matched and how to retrieve them. To opt out of the rewrite, wrap a value in parentheses (e.g. ‘(donor derived cell therapy)’) and it is sent verbatim as a loose keyword match.

Parameters:

  • intervention (string) (required) Drug, biologic, device, or intervention name (e.g., ‘nivolumab’, ‘CRISPR’, ‘CAR-T cells’, ‘metformin’, ‘osimertinib’). Matched against each study’s registered intervention names and synonyms (InterventionName/InterventionOtherName), not free text in study summaries, and multi-word values are matched as an EXACT PHRASE – so ‘donor derived cell therapy’ matches 0 studies even though 251 trials match the same words loosely. For looser matching, wrap the value in parentheses (e.g. ‘(donor derived cell therapy)’) to send it verbatim, or use ClinicalTrials_search_studies with query_term for free text across all study fields. Prefer the generic/INN name over a brand name. See executed_query and relaxed_match_check in the response.

  • condition ([‘string’, ‘null’]) (optional) Disease or condition to filter trials (e.g., ‘HER2 breast cancer’, ‘NSCLC KRAS G12C’). Alias for query_cond. Multi-word values are matched as an exact phrase (e.g. ‘kidney transplantation’ is sent as “kidney transplantation”), which is narrower than a loose keyword match. For looser matching, wrap the value in parentheses (e.g. ‘(kidney transplantation)’) to send it verbatim. Values already containing Essie syntax (AND/OR/NOT/AREA[]/quotes) are passed through unchanged. See executed_query in the response for what actually ran.

  • status ([‘string’, ‘null’]) (optional) Recruitment status filter: ‘RECRUITING’, ‘COMPLETED’, ‘ACTIVE_NOT_RECRUITING’, ‘TERMINATED’. Alias for filter_status.

  • filter_status ([‘string’, ‘null’]) (optional) Filter by recruitment status: ‘RECRUITING’, ‘COMPLETED’, ‘ACTIVE_NOT_RECRUITING’, ‘TERMINATED’. Comma-separate multiple.

  • filter_phase ([‘string’, ‘null’]) (optional) Filter by trial phase: ‘PHASE1’, ‘PHASE2’, ‘PHASE3’, ‘PHASE4’. Comma-separate multiple.

  • page_size (integer) (optional) Number of results per page (default 10, max 1000).

Example Usage:

query = {
    "name": "ClinicalTrials_search_by_intervention",
    "arguments": {
        "intervention": "example_value"
    }
}
result = tu.run(query)

ClinicalTrials_search_by_sponsor (Type: ClinicalTrialsTool)#

Search ClinicalTrials.gov for clinical trials by sponsor or lead organization. Returns trials fun…

ClinicalTrials_search_by_sponsor tool specification

Tool Information:

  • Name: ClinicalTrials_search_by_sponsor

  • Type: ClinicalTrialsTool

  • Description: Search ClinicalTrials.gov for clinical trials by sponsor or lead organization. Returns trials funded by pharmaceutical companies, academic institutions, or government agencies. Example: find all Phase 3 trials sponsored by ‘National Cancer Institute’ for cancer conditions. Query rewriting: multi-word intervention/condition/sponsor values are sent to ClinicalTrials.gov as an EXACT PHRASE, and intervention/sponsor values are further restricted to specific registry fields, so a phrase no registrant recorded verbatim can match 0 studies even when many trials mention it. The query actually executed is always returned in executed_query (with per-parameter detail in query_rewrites); when a rewritten query matches nothing, relaxed_match_check reports how many studies your original wording would have matched and how to retrieve them. To opt out of the rewrite, wrap a value in parentheses (e.g. ‘(donor derived cell therapy)’) and it is sent verbatim as a loose keyword match.

Parameters:

  • sponsor (string) (required) Sponsor or lead organization name (e.g., ‘Pfizer’, ‘National Cancer Institute’, ‘Novartis’, ‘Johns Hopkins University’, ‘Merck’). Matched against each study’s registered lead-sponsor name (AREA[LeadSponsorName]) only, and multi-word values are matched as an EXACT PHRASE. For looser matching, wrap the value in parentheses (e.g. ‘(National Cancer Institute)’) to send it verbatim. See executed_query and relaxed_match_check in the response.

  • query_cond ([‘string’, ‘null’]) (optional) Optional disease/condition filter (e.g., ‘cancer’, ‘cardiovascular disease’, ‘alzheimer’). Multi-word values are matched as an exact phrase (e.g. ‘kidney transplantation’ is sent as “kidney transplantation”), which is narrower than a loose keyword match. For looser matching, wrap the value in parentheses (e.g. ‘(kidney transplantation)’) to send it verbatim. Values already containing Essie syntax (AND/OR/NOT/AREA[]/quotes) are passed through unchanged. See executed_query in the response for what actually ran.

  • filter_status ([‘string’, ‘null’]) (optional) Filter by status: ‘RECRUITING’, ‘COMPLETED’, ‘ACTIVE_NOT_RECRUITING’. Comma-separate multiple.

  • filter_phase ([‘string’, ‘null’]) (optional) Filter by phase: ‘PHASE1’, ‘PHASE2’, ‘PHASE3’, ‘PHASE4’. Comma-separate multiple.

  • page_size (integer) (optional) Number of results per page (default 10, max 1000).

Example Usage:

query = {
    "name": "ClinicalTrials_search_by_sponsor",
    "arguments": {
        "sponsor": "example_value"
    }
}
result = tu.run(query)

ClinicalTrials_search_studies (Type: ClinicalTrialsTool)#

Search ClinicalTrials.gov for clinical trial studies by condition, intervention, sponsor, or othe…

ClinicalTrials_search_studies tool specification

Tool Information:

  • Name: ClinicalTrials_search_studies

  • Type: ClinicalTrialsTool

  • Description: Search ClinicalTrials.gov for clinical trial studies by condition, intervention, sponsor, or other criteria. Returns NCT IDs, titles, status, phase, enrollment, and key trial metadata. Example: search for ‘breast cancer’ trials with ‘pembrolizumab’ that are RECRUITING in Phase 3. Query rewriting: multi-word intervention/condition/sponsor values are sent to ClinicalTrials.gov as an EXACT PHRASE, and intervention/sponsor values are further restricted to specific registry fields, so a phrase no registrant recorded verbatim can match 0 studies even when many trials mention it. The query actually executed is always returned in executed_query (with per-parameter detail in query_rewrites); when a rewritten query matches nothing, relaxed_match_check reports how many studies your original wording would have matched and how to retrieve them. To opt out of the rewrite, wrap a value in parentheses (e.g. ‘(donor derived cell therapy)’) and it is sent verbatim as a loose keyword match.

Parameters:

  • operation (string) (optional) Operation (optional; defaults to ‘search’ for this tool).

  • query_cond ([‘string’, ‘null’]) (optional) Disease or condition to search for (e.g., ‘breast cancer’, ‘type 2 diabetes’, ‘COVID-19’). Supports Boolean operators (AND, OR, NOT). Multi-word values are matched as an exact phrase (e.g. ‘kidney transplantation’ is sent as “kidney transplantation”), which is narrower than a loose keyword match. For looser matching, wrap the value in parentheses (e.g. ‘(kidney transplantation)’) to send it verbatim. Values already containing Essie syntax (AND/OR/NOT/AREA[]/quotes) are passed through unchanged. See executed_query in the response for what actually ran.

  • query_intr ([‘string’, ‘null’]) (optional) Intervention or drug to search for (e.g., ‘pembrolizumab’, ‘metformin’, ‘chemotherapy’). Matched against each study’s registered intervention names and synonyms (InterventionName/InterventionOtherName), not free text in study summaries, and multi-word values are matched as an EXACT PHRASE – so ‘donor derived cell therapy’ matches 0 studies even though 251 trials match the same words loosely. For looser matching, wrap the value in parentheses (e.g. ‘(donor derived cell therapy)’) to send it verbatim, or use ClinicalTrials_search_studies with query_term for free text across all study fields. Prefer the generic/INN name over a brand name. See executed_query and relaxed_match_check in the response.

  • query_term ([‘string’, ‘null’]) (optional) Free-text search across all study fields. Use for general keyword search.

  • filter_status ([‘string’, ‘null’]) (optional) Filter by recruitment status. Options: ‘RECRUITING’, ‘NOT_YET_RECRUITING’, ‘ACTIVE_NOT_RECRUITING’, ‘COMPLETED’, ‘WITHDRAWN’, ‘SUSPENDED’, ‘TERMINATED’, ‘ENROLLING_BY_INVITATION’. Comma-separate multiple values.

  • filter_phase ([‘string’, ‘null’]) (optional) Filter by trial phase. Options: ‘EARLY_PHASE1’, ‘PHASE1’, ‘PHASE2’, ‘PHASE3’, ‘PHASE4’, ‘NA’. Comma-separate multiple (e.g., ‘PHASE2,PHASE3’).

  • filter_study_type ([‘string’, ‘null’]) (optional) Filter by study type: ‘INTERVENTIONAL’, ‘OBSERVATIONAL’, ‘EXPANDED_ACCESS’.

  • page_size (integer) (optional) Number of results per page (default 10, max 1000).

  • next_page_token ([‘string’, ‘null’]) (optional) Token for retrieving the next page of results (obtained from previous response).

  • query ([‘string’, ‘null’]) (optional) General keyword search across all fields. Alias for query_term. E.g., “FLT3 AML”, “KRAS NSCLC”.

  • condition ([‘string’, ‘null’]) (optional) Disease or condition to search for. Alias for query_cond. E.g., “acute myeloid leukemia”. Multi-word values are matched as an exact phrase (e.g. ‘kidney transplantation’ is sent as “kidney transplantation”), which is narrower than a loose keyword match. For looser matching, wrap the value in parentheses (e.g. ‘(kidney transplantation)’) to send it verbatim. Values already containing Essie syntax (AND/OR/NOT/AREA[]/quotes) are passed through unchanged. See executed_query in the response for what actually ran.

  • status ([‘string’, ‘null’]) (optional) Recruitment status filter. Alias for filter_status. E.g., “RECRUITING”, “COMPLETED”.

  • max_results ([‘integer’, ‘null’]) (optional) Maximum number of results to return. Alias for page_size.

  • intervention ([‘string’, ‘null’]) (optional) Intervention or drug to search for. Alias for query_intr. E.g., “pembrolizumab”, “metformin”. Matched against each study’s registered intervention names and synonyms (InterventionName/InterventionOtherName), not free text in study summaries, and multi-word values are matched as an EXACT PHRASE – so ‘donor derived cell therapy’ matches 0 studies even though 251 trials match the same words loosely. For looser matching, wrap the value in parentheses (e.g. ‘(donor derived cell therapy)’) to send it verbatim, or use ClinicalTrials_search_studies with query_term for free text across all study fields. Prefer the generic/INN name over a brand name. See executed_query and relaxed_match_check in the response.

  • sponsor ([‘string’, ‘null’]) (optional) Lead sponsor or collaborator name to search for. E.g., “National Cancer Institute”. Matched against each study’s registered lead-sponsor name (AREA[LeadSponsorName]) only, and multi-word values are matched as an EXACT PHRASE. For looser matching, wrap the value in parentheses (e.g. ‘(National Cancer Institute)’) to send it verbatim. See executed_query and relaxed_match_check in the response.

Example Usage:

query = {
    "name": "ClinicalTrials_search_studies",
    "arguments": {
    }
}
result = tu.run(query)

extract_clinical_trial_adverse_events (Type: ClinicalTrialsDetailsTool)#

Extracts detailed adverse event results from clinicaltrials.gov, using their NCT IDs.

extract_clinical_trial_adverse_events tool specification

Tool Information:

  • Name: extract_clinical_trial_adverse_events

  • Type: ClinicalTrialsDetailsTool

  • Description: Extracts detailed adverse event results from clinicaltrials.gov, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • organ_systems (array) (optional) List of organs or organ systems to filter adverse events (see enum for exact text). Adverse events will be matched only if the input exactly matches their terms (case agnostic). If not specified, all adverse events will be returned. By default, all adverse events will be returned.

  • adverse_event_type (string) (optional) Type of adverse events to extract. Options are ‘serious’ (serious adverse events only), ‘other’ (non-serious adverse events only), ‘all’ (all adverse events), or specific event names such as ‘nausea’, ‘neutropenia’, ‘epilepsy’ (from MedDRA). For specific event names, adverse events will be matched as long as the input partially matches their terms (case agnostic). Querying for specific adverse event names is recommended as there are typically many adverse events logged. If querying for specific event names does not return any results, this parameter should be set to ‘serious’ for sanity check. By default, the value is set to ‘serious’, i.e. the tool will extract all serious adverse events.

Example Usage:

query = {
    "name": "extract_clinical_trial_adverse_events",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

extract_clinical_trial_outcomes (Type: ClinicalTrialsDetailsTool)#

Extracts detailed trial outcome results (e.g., overall survival months, p-values, etc.) from clin…

extract_clinical_trial_outcomes tool specification

Tool Information:

  • Name: extract_clinical_trial_outcomes

  • Type: ClinicalTrialsDetailsTool

  • Description: Extracts detailed trial outcome results (e.g., overall survival months, p-values, etc.) from clinicaltrials.gov, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • outcome_measure (string) (optional) Outcome measure to extract. Example values include ‘primary’ (primary outcomes only), ‘secondary’ (secondary outcomes only), ‘all’ (all outcomes), or specific measure names such as ‘survival’, ‘overall survival’. For specific measure names, outcome measures will be matched as long as the input partially matches their titles or descriptions (case agnostic). Querying for specific measure names is recommended after getting an overview of outcome measures (‘primary’). If querying for specific measure names does not return any results, this parameter should be set to ‘primary’ for sanity check. By default, the value is set to ‘primary’, i.e. the tool will extract all primary outcome results.

Example Usage:

query = {
    "name": "extract_clinical_trial_outcomes",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

get_clinical_trial_conditions_and_interventions (Type: ClinicalTrialsDetailsTool)#

Retrieves the list of conditions or diseases and the interventions and arm groups that the clinic…

get_clinical_trial_conditions_and_interventions tool specification

Tool Information:

  • Name: get_clinical_trial_conditions_and_interventions

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves the list of conditions or diseases and the interventions and arm groups that the clinical trials are focused on, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • condition_and_intervention (string) (optional) Unused filter parameter, kept for backward compatibility. Can be omitted or set to any string.

Example Usage:

query = {
    "name": "get_clinical_trial_conditions_and_interventions",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

get_clinical_trial_descriptions (Type: ClinicalTrialsDetailsTool)#

Retrieves detailed identification information for trials, including titles, phases, and descripti…

get_clinical_trial_descriptions tool specification

Tool Information:

  • Name: get_clinical_trial_descriptions

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves detailed identification information for trials, including titles, phases, and descriptions, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • description_type (string) (required) Type of information to retrieve. Options are ‘brief’ for brief descriptions or ‘full’ for full descriptions.

Example Usage:

query = {
    "name": "get_clinical_trial_descriptions",
    "arguments": {
        "nct_ids": ["item1", "item2"],
        "description_type": "example_value"
    }
}
result = tu.run(query)

get_clinical_trial_eligibility_criteria (Type: ClinicalTrialsDetailsTool)#

Retrieves the eligibility criteria for the clinical trials, using their NCT IDs.

get_clinical_trial_eligibility_criteria tool specification

Tool Information:

  • Name: get_clinical_trial_eligibility_criteria

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves the eligibility criteria for the clinical trials, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • eligibility_criteria (string) (optional) Unused filter parameter, kept for backward compatibility. Can be omitted or set to any string.

Example Usage:

query = {
    "name": "get_clinical_trial_eligibility_criteria",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

get_clinical_trial_locations (Type: ClinicalTrialsDetailsTool)#

Retrieves the locations where the clinical trials are being conducted, using their NCT IDs.

get_clinical_trial_locations tool specification

Tool Information:

  • Name: get_clinical_trial_locations

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves the locations where the clinical trials are being conducted, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • location (string) (optional) Unused filter parameter, kept for backward compatibility. Can be omitted or set to any string.

Example Usage:

query = {
    "name": "get_clinical_trial_locations",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

get_clinical_trial_outcome_measures (Type: ClinicalTrialsDetailsTool)#

Retrieves the outcome measures for the clinical trials, using their NCT IDs.

get_clinical_trial_outcome_measures tool specification

Tool Information:

  • Name: get_clinical_trial_outcome_measures

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves the outcome measures for the clinical trials, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • outcome_measures (string) (optional) Decides whether to retrieve primary, secondary, or all outcome measures. Options are ‘primary’, ‘secondary’, or ‘all’. Default is ‘primary’.

Example Usage:

query = {
    "name": "get_clinical_trial_outcome_measures",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

get_clinical_trial_references (Type: ClinicalTrialsDetailsTool)#

Retrieves the references (if any) for the clinical trials, using their NCT IDs.

get_clinical_trial_references tool specification

Tool Information:

  • Name: get_clinical_trial_references

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves the references (if any) for the clinical trials, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • references (string) (optional) Unused filter parameter, kept for backward compatibility. Can be omitted or set to any string.

Example Usage:

query = {
    "name": "get_clinical_trial_references",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

get_clinical_trial_status_and_dates (Type: ClinicalTrialsDetailsTool)#

Retrieves trial status and start and completion dates, using their NCT IDs.

get_clinical_trial_status_and_dates tool specification

Tool Information:

  • Name: get_clinical_trial_status_and_dates

  • Type: ClinicalTrialsDetailsTool

  • Description: Retrieves trial status and start and completion dates, using their NCT IDs.

Parameters:

  • nct_ids (array) (required) List of NCT IDs of the clinical trials (e.g., [‘NCT04852770’, ‘NCT01728545’]).

  • status_and_date (string) (optional) Unused filter parameter, kept for backward compatibility. Can be omitted or set to any string.

Example Usage:

query = {
    "name": "get_clinical_trial_status_and_dates",
    "arguments": {
        "nct_ids": ["item1", "item2"]
    }
}
result = tu.run(query)

search_clinical_trials (Type: ClinicalTrialsSearchTool)#

Search ClinicalTrials.gov for clinical trials by disease/condition, drug/intervention, or keyword…

search_clinical_trials tool specification

Tool Information:

  • Name: search_clinical_trials

  • Type: ClinicalTrialsSearchTool

  • Description: Search ClinicalTrials.gov for clinical trials by disease/condition, drug/intervention, or keywords. This is the PRIMARY tool for finding clinical trials — use it when you need to discover trials for a drug (e.g., ‘olaparib’, ‘pembrolizumab’), a disease (e.g., ‘lung cancer’, ‘diabetes’), or any study criteria. Accepts condition names, intervention/treatment names, and free-text queries. Returns NCT IDs and brief descriptions with pagination. Use the returned NCT IDs with ‘get_clinical_trial_*’ tools for detailed protocol info, or ‘extract_clinical_trial_*’ tools for efficacy/safety results. Limited to trials beyond phase 1. Query rewriting: multi-word intervention values are matched as an EXACT PHRASE against each study’s registered intervention names/synonyms, so a phrase no registrant recorded verbatim can match 0 studies even when many trials mention it. The query actually executed is returned in executed_query (detail in query_rewrites), and a zero-hit rewritten query reports in relaxed_match_check how many studies your original wording would have matched. Wrap a value in parentheses (e.g. ‘(cell therapy)’) to send it verbatim.

Parameters:

  • condition (string) (optional) Query for condition or disease using Essie expression syntax (e.g., ‘lung cancer’, ‘(head OR neck) AND pain AND NOT “back pain”’). Sent to ClinicalTrials.gov verbatim (this tool does not rewrite condition values); see executed_query in the response for what actually ran.

  • intervention (string) (optional) Query for intervention/treatment using Essie expression syntax (e.g., ‘chemotherapy’, ‘immunotherapy’, ‘olaparib’, ‘combination therapy’). Matched against each study’s registered intervention names and synonyms (InterventionName/InterventionOtherName), not free text in study summaries, so prefer the generic/INN name: a brand name that no registrant recorded in either field can return zero results. Values that already contain Essie syntax (AREA[…]/AND/OR/NOT/quotes) are passed through unchanged. Matched against each study’s registered intervention names and synonyms (InterventionName/InterventionOtherName), not free text in study summaries, and multi-word values are matched as an EXACT PHRASE – so ‘donor derived cell therapy’ matches 0 studies even though 251 trials match the same words loosely. For looser matching, wrap the value in parentheses (e.g. ‘(donor derived cell therapy)’) to send it verbatim, or use ClinicalTrials_search_studies with query_term for free text across all study fields. Prefer the generic/INN name over a brand name. See executed_query and relaxed_match_check in the response.

  • query_term (string) (optional) Query for ‘other terms’ with Essie expression syntax (e.g., ‘combination’, ‘AREA[LastUpdatePostDate]RANGE[2023-01-15,MAX]’, ‘Phase II’). Can be used to search for all other protocol fields, including but not limited to title, outcome measures, status, phase, location, etc.

  • pageSize (integer) (optional) Maximum number of studies to return per page (default 10, max 1000).

  • pageToken (string) (optional) Token to retrieve the next page of results, obtained from the ‘nextPageToken’ field of the previous response. Do not specify it for first page. When you make an initial request to the API which supports pagination, the response will include a nextPageToken. This token can then be used as a parameter in the subsequent API request to retrieve the next set of data.

  • overall_status (array) (optional) Filter by overall study status (e.g., [‘RECRUITING’], [‘COMPLETED’], [‘RECRUITING’, ‘NOT_YET_RECRUITING’]). Valid values: RECRUITING, NOT_YET_RECRUITING, ACTIVE_NOT_RECRUITING, COMPLETED, ENROLLING_BY_INVITATION, SUSPENDED, TERMINATED, WITHDRAWN.

  • max_results (integer) (optional) Maximum number of studies to return (alias for pageSize, default 10, max 1000).

  • limit (integer) (optional) Alias for max_results: maximum number of studies to return (default 10, max 1000).

  • status (unknown) (optional) Alias for overall_status. Filter by trial status, e.g. “RECRUITING”, “COMPLETED”.

  • keyword (string) (optional) Alias for query_term. Free-text keyword search across all trial fields (e.g., drug name, condition, investigator).

Example Usage:

query = {
    "name": "search_clinical_trials",
    "arguments": {
    }
}
result = tu.run(query)