Skip to main content
Glama

Clinicaltrials Find Eligible

clinicaltrials_find_eligible
Read-onlyIdempotent

Find candidate clinical trials for a patient profile. Provide age, sex, conditions, and location to get studies with their demographic limits, contact information, and recruiting locations. Candidates are matched on age, sex, location, recruitment status, and ClinicalTrials.gov's fuzzy condition search only — inclusion/exclusion criteria are not checked, and a candidate can exclude the requested condition, so review each one's criteria with clinicaltrials_get_study_record before treating it as a match. Results are re-ranked so studies whose own condition matches a requested condition surface above tangential matches from ClinicalTrials.gov's fuzzy condition search. Each candidate returns only the sites matching the requested location (capped by locationLimit), not the study's full registered site list — a large trial can register hundreds of sites worldwide. When none of a candidate's matched sites is recruiting, one recruiting site is added so an enrollable site is never hidden behind a closer closed one: the one nearest the matched sites by their published coordinates, in the requested country whenever a site there recruits, carrying distanceMi, or the first in match order when coordinates are missing. Fetch a study's complete record with clinicaltrials_get_study_record.

Input Schema

NameRequiredDescriptionDefault
ageYesPatient age as a whole number in ageUnit (years unless ageUnit says otherwise).
sexYesPatient's biological sex. Use 'ALL' to include studies regardless of sex restrictions.
ageUnitNoUnit age is given in: years (default), months, weeks, or days; case and singular forms are accepted. Use a smaller unit for an infant or young child whose eligibility window is narrower than a year — age 7 with ageUnit "months" matches a study registered for 6 Months to 8 Months, which no whole number of years reaches. ClinicalTrials.gov compares ages across units, so the unit only sets how precisely age is stated.
locationYesPatient location as `{ country (required), state?, city? }`. Country is required; state/city narrow the match. Every part given must hold for the same study site: country and state are compared with the site's filed country and state, while city is matched against the site's whole location text, so a site filed under a borough or neighbouring town that names the city still counts. For radius-based geographic search, use clinicaltrials_search_studies with geoFilter.
conditionsYesMedical conditions or diagnoses, e.g. ["Type 2 Diabetes", "Hypertension"]. Each entry is matched as a condition: an entry containing whitespace is quoted and matches as a phrase, and any other entry is sent as written, punctuation included (double quotes are stripped from every entry); multiple entries are combined with OR, so studies for any listed condition qualify. Returned studies are re-ranked so those whose own condition list names a requested condition rank above tangential matches the upstream fuzzy search pulls in via the MeSH umbrella.
maxResultsNoMaximum candidates to return, 1–1000. Each call returns at most 50; a larger value returns 50, reported in truncated/shown/cap when more studies match, and the searchCriteria replay through clinicaltrials_search_studies pages the rest.
locationLimitNoCap on the sites returned per candidate. Each candidate keeps only the sites matching the requested location at the narrowest level that matched (city, else state, else country), capped at this many; the rest of the study's registered sites are omitted. The cap governs those matched sites — when none of them is recruiting, one recruiting site is added on top of it (the nearest to any matched site, measured before this cap, when coordinates allow — in the requested country whenever a site there recruits), so a candidate can carry one site more than this. Raise it to see more nearby sites — there is no upper bound, and a limit past the matched sites returns all of them — or fetch the complete site list with clinicaltrials_get_study_record. Each candidate reports totalLocations / matchedLocations / locationsTruncated / nearestRecruitingSiteAdded in locationSummary only when the bound actually dropped sites.
recruitingOnlyNoOnly include actively recruiting studies.
healthyVolunteerNoWhether the patient is a healthy volunteer. When true, only studies accepting healthy volunteers are queried.

Output Schema

NameRequiredDescriptionDefault
capNoThe tool's per-call cap, served in place of the requested maxResults when truncated is true.
errorNoPresent when the call failed. Absent on success.
shownNoCandidates returned when truncated is true.
funnelNoMatch counts at each filter stage. Shows where the funnel collapsed — e.g., conditionMatched=298 but demographicsMatched=2 means age/sex/status are the constraint.
noticeNoWhen no studies matched, recovery guidance that identifies which filter stage collapsed and suggests how to broaden. When studies are returned, one caveat for the whole response: candidates were matched on demographics, location, recruitment status, and a fuzzy condition search, not on inclusion/exclusion criteria. When maxResults was above the tool's per-call cap and more studies match, a sentence follows stating the requested, served, and total counts and pointing at the searchCriteria replay.
studiesNoCandidate studies with their demographic limits (age, sex, healthy volunteers), contacts, and location fields — matched on age, sex, location, recruitment status, and the fuzzy condition search; inclusion/exclusion criteria are not checked and are not in these records, so review each candidate with clinicaltrials_get_study_record. Each candidate's protocolSection.contactsLocationsModule.locations is BOUNDED to the sites matching the requested location (capped at locationLimit) plus, when none of those is recruiting, one added recruiting site — not the study's full registered site list. The added site is the one nearest any matched site by published coordinates, taken from the requested country whenever a site there recruits, and carries distanceMi (miles to that nearest matched site); when the matched or recruiting sites publish no coordinates it is the first in match order and carries no distanceMi. A candidate whose sites were bounded also carries a top-level locationSummary object — { totalLocations, matchedLocations, locationsTruncated, nearestRecruitingSiteAdded?, retrieveFullStudyWith } — absent when nothing was dropped; nearestRecruitingSiteAdded is present only when that extra site was added (the key keeps its name in the match-order fallback). Fetch a study's complete record and site list with clinicaltrials_get_study_record.
truncatedNoTrue when maxResults was above the tool's per-call cap and more studies match than were returned. Absent otherwise.
totalCountNoTotal matching studies from the API.
searchCriteriaNoNormalized search criteria applied to this eligibility query, including the exact upstream query strings needed to reproduce the full match set via clinicaltrials_search_studies (replay with includeUnknownEnrollment=true, which find_eligible always sets).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / location / properties / country / description
      Previous value: -"Country name. E.g., \"United States\"."New value: +"Country name, e.g. \"United States\". Common synonyms rank sites as the registry spelling does: USA and US as United States, UK and England as United Kingdom, Czech Republic as Czechia, Republic of Korea as South Korea, and PR, GU, VI, AS, and MP as the US territories, which the registry files as countries."
    • changedInput schema / properties / location / properties / state / description
      Previous value: -"State or province, compared with the state the site files. With city also given, a site that files no state still matches; without city, only sites filing this state match."New value: +"State or province, compared with the state the site files. A US state or DC abbreviation (WA, DC) is compared as its full name when the country is the United States or a synonym for it. With city also given, a site that files no state still matches; without city, only sites filing this state match."
  2. Changed5 schema fields changed
    • changedInput schema / properties / location / description
      Previous value: -"Patient location as `{ country (required), state?, city? }`. Country is required; state/city narrow the match. For radius-based geographic search, use clinicaltrials_search_studies with geoFilter."New value: +"Patient location as `{ country (required), state?, city? }`. Country is required; state/city narrow the match. Every part given must hold for the same study site: country and state are compared with the site's filed country and state, while city is matched against the site's whole location text, so a site filed under a borough or neighbouring town that names the city still counts. For radius-based geographic search, use clinicaltrials_search_studies with geoFilter."
    • changedInput schema / properties / location / properties / state / description
      Previous value: -"State or province."New value: +"State or province, compared with the state the site files. With city also given, a site that files no state still matches; without city, only sites filing this state match."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `blank_value`: A conditions entry or location.country was supplied blank — empty, whitespace-only, or made only of `\"` characters, invisible format characters such as zero-width spaces, and whitespace, since `\"` is stripped before the query is built — or conditions was an empty list. `rate_limited`: ClinicalTrials.gov returned 429 after retry budget exhausted. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `blank_value`: A conditions entry or location.country was supplied blank — empty, whitespace-only, or made only of `\"` characters, invisible format characters such as zero-width spaces, and whitespace, since `\"` is stripped before the query is built — or conditions was an empty list. `field_invalid`: A conditions entry carries an AREA[] expression naming a field ClinicalTrials.gov does not recognize or cannot search by value. `query_parse_error`: A conditions entry uses syntax the upstream Essie parser rejects — typically an unmatched `(` or `)`, or a `[` or `]` outside an AREA[…] expression. `request_too_long`: The conditions list or location makes the request URL longer than ClinicalTrials.gov accepts — several hundred conditions in one call. `rate_limited`: ClinicalTrials.gov returned 429 after retry budget exhausted. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "blank_value",
      -  "rate_limited"
      -]New value: +[
      +  "blank_value",
      +  "field_invalid",
      +  "query_parse_error",
      +  "request_too_long",
      +  "rate_limited"
      +]
    • changedOutput schema / properties / searchCriteria / properties / location / description
      Previous value: -"The exact queryLocn string sent upstream: city/state/country AND-joined inside SEARCH[Location](…) so every part must match the same site, each part quoted unless it is a single run of letters and digits (Toronto stays bare; \"United States\", \"Winston-Salem\", and \"L'Aquila\" are quoted), with any embedded double quote stripped and any backslash in a quoted part doubled. Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."New value: +"The exact queryLocn string sent upstream: the parts AND-joined inside SEARCH[Location](…) so every part must match the same site. The city is a search term, quoted unless it is a single run of letters and digits (Toronto stays bare; \"Winston-Salem\" and \"L'Aquila\" are quoted); the state is AREA[LocationState]\"…\", ORed with AREA[LocationState]MISSING when a city is given; the country is AREA[LocationCountry]\"…\", ORed with the same spelling without diacritics when it carries any (México also tries Mexico). Any embedded double quote is stripped and any backslash in a quoted value doubled. Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."
  3. Changed14 schema fields changed
    • changedInput schema / properties / age / description
      Previous value: -"Patient age in years."New value: +"Patient age as a whole number in ageUnit (years unless ageUnit says otherwise)."
    • addedInput schema / properties / ageUnit
      Added value: +{
      +  "description": "Unit age is given in: years (default), months, weeks, or days; case and singular forms are accepted. Use a smaller unit for an infant or young child whose eligibility window is narrower than a year — age 7 with ageUnit \"months\" matches a study registered for 6 Months to 8 Months, which no whole number of years reaches. ClinicalTrials.gov compares ages across units, so the unit only sets how precisely age is stated.",
      +  "enum": [
      +    "years",
      +    "months",
      +    "weeks",
      +    "days"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / conditions / description
      Previous value: -"Medical conditions or diagnoses, e.g. [\"Type 2 Diabetes\", \"Hypertension\"]. Each entry is matched as a condition (multi-word entries match as a phrase); multiple entries are combined with OR, so studies for any listed condition qualify. Returned studies are re-ranked so those whose own condition list names a requested condition rank above tangential matches the upstream fuzzy search pulls in via the MeSH umbrella."New value: +"Medical conditions or diagnoses, e.g. [\"Type 2 Diabetes\", \"Hypertension\"]. Each entry is matched as a condition: an entry containing whitespace is quoted and matches as a phrase, and any other entry is sent as written, punctuation included (double quotes are stripped from every entry); multiple entries are combined with OR, so studies for any listed condition qualify. Returned studies are re-ranked so those whose own condition list names a requested condition rank above tangential matches the upstream fuzzy search pulls in via the MeSH umbrella."
    • changedInput schema / properties / locationLimit / description
      Previous value: -"Cap on the sites returned per candidate. Each candidate keeps only the sites matching the requested location at the narrowest level that matched (city, else state, else country), capped at this many; the rest of the study's registered sites are omitted. The cap governs those matched sites — when none of them is recruiting, one recruiting site is added on top of it (the nearest to any matched site, measured before this cap, when coordinates allow — in the requested country whenever a site there recruits), so a candidate can carry one site more than this. Raise it to see more nearby sites, or fetch the complete site list with clinicaltrials_get_study_record. Each candidate reports totalLocations / matchedLocations / locationsTruncated / nearestRecruitingSiteAdded in locationSummary only when the bound actually dropped sites."New value: +"Cap on the sites returned per candidate. Each candidate keeps only the sites matching the requested location at the narrowest level that matched (city, else state, else country), capped at this many; the rest of the study's registered sites are omitted. The cap governs those matched sites — when none of them is recruiting, one recruiting site is added on top of it (the nearest to any matched site, measured before this cap, when coordinates allow — in the requested country whenever a site there recruits), so a candidate can carry one site more than this. Raise it to see more nearby sites — there is no upper bound, and a limit past the matched sites returns all of them — or fetch the complete site list with clinicaltrials_get_study_record. Each candidate reports totalLocations / matchedLocations / locationsTruncated / nearestRecruitingSiteAdded in locationSummary only when the bound actually dropped sites."
    • changedInput schema / properties / locationLimit / maximum
      Previous value: -500New value: +9007199254740991
    • changedInput schema / properties / maxResults / description
      Previous value: -"Maximum results to return."New value: +"Maximum candidates to return, 1–1000. Each call returns at most 50; a larger value returns 50, reported in truncated/shown/cap when more studies match, and the searchCriteria replay through clinicaltrials_search_studies pages the rest."
    • changedInput schema / properties / maxResults / maximum
      Previous value: -50New value: +1000
    • addedOutput schema / properties / cap
      Added value: +{
      +  "description": "The tool's per-call cap, served in place of the requested maxResults when truncated is true.",
      +  "exclusiveMinimum": 0,
      +  "maximum": 9007199254740991,
      +  "type": "integer"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"When no studies matched, recovery guidance that identifies which filter stage collapsed and suggests how to broaden. When studies are returned, one caveat for the whole response: candidates were matched on demographics, location, recruitment status, and a fuzzy condition search, not on inclusion/exclusion criteria."New value: +"When no studies matched, recovery guidance that identifies which filter stage collapsed and suggests how to broaden. When studies are returned, one caveat for the whole response: candidates were matched on demographics, location, recruitment status, and a fuzzy condition search, not on inclusion/exclusion criteria. When maxResults was above the tool's per-call cap and more studies match, a sentence follows stating the requested, served, and total counts and pointing at the searchCriteria replay."
    • changedOutput schema / properties / searchCriteria / properties / age / description
      Previous value: -"Patient age."New value: +"Patient age, in ageUnit when present, else in years."
    • addedOutput schema / properties / searchCriteria / properties / ageUnit
      Added value: +{
      +  "description": "The unit age was given in. Present only for months, weeks, or days; absent means years.",
      +  "enum": [
      +    "years",
      +    "months",
      +    "weeks",
      +    "days"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / searchCriteria / properties / location / description
      Previous value: -"The exact queryLocn string sent upstream (city/state/country, multi-word components quoted, AND-joined). Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."New value: +"The exact queryLocn string sent upstream: city/state/country AND-joined inside SEARCH[Location](…) so every part must match the same site, each part quoted unless it is a single run of letters and digits (Toronto stays bare; \"United States\", \"Winston-Salem\", and \"L'Aquila\" are quoted), with any embedded double quote stripped and any backslash in a quoted part doubled. Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."
    • addedOutput schema / properties / shown
      Added value: +{
      +  "description": "Candidates returned when truncated is true.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / truncated
      Added value: +{
      +  "description": "True when maxResults was above the tool's per-call cap and more studies match than were returned. Absent otherwise.",
      +  "type": "boolean"
      +}
  4. Changed3 schema fields changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `blank_value`: A parameter was supplied with a blank, whitespace-only, or empty-list value. `rate_limited`: ClinicalTrials.gov returned 429 after retry budget exhausted. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `blank_value`: A conditions entry or location.country was supplied blank — empty, whitespace-only, or made only of `\"` characters, invisible format characters such as zero-width spaces, and whitespace, since `\"` is stripped before the query is built — or conditions was an empty list. `rate_limited`: ClinicalTrials.gov returned 429 after retry budget exhausted. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / notice / description
      Previous value: -"Recovery guidance when no studies matched — identifies which filter stage collapsed and suggests how to broaden. Absent when results are returned."New value: +"When no studies matched, recovery guidance that identifies which filter stage collapsed and suggests how to broaden. When studies are returned, one caveat for the whole response: candidates were matched on demographics, location, recruitment status, and a fuzzy condition search, not on inclusion/exclusion criteria."
    • changedOutput schema / properties / studies / description
      Previous value: -"Matching studies with eligibility and location fields. Each candidate's protocolSection.contactsLocationsModule.locations is BOUNDED to the sites matching the requested location (capped at locationLimit) plus, when none of those is recruiting, one added recruiting site — not the study's full registered site list. The added site is the one nearest any matched site by published coordinates, taken from the requested country whenever a site there recruits, and carries distanceMi (miles to that nearest matched site); when the matched or recruiting sites publish no coordinates it is the first in match order and carries no distanceMi. A candidate whose sites were bounded also carries a top-level locationSummary object — { totalLocations, matchedLocations, locationsTruncated, nearestRecruitingSiteAdded?, retrieveFullStudyWith } — absent when nothing was dropped; nearestRecruitingSiteAdded is present only when that extra site was added (the key keeps its name in the match-order fallback). Fetch a study's complete record and site list with clinicaltrials_get_study_record."New value: +"Candidate studies with their demographic limits (age, sex, healthy volunteers), contacts, and location fields — matched on age, sex, location, recruitment status, and the fuzzy condition search; inclusion/exclusion criteria are not checked and are not in these records, so review each candidate with clinicaltrials_get_study_record. Each candidate's protocolSection.contactsLocationsModule.locations is BOUNDED to the sites matching the requested location (capped at locationLimit) plus, when none of those is recruiting, one added recruiting site — not the study's full registered site list. The added site is the one nearest any matched site by published coordinates, taken from the requested country whenever a site there recruits, and carries distanceMi (miles to that nearest matched site); when the matched or recruiting sites publish no coordinates it is the first in match order and carries no distanceMi. A candidate whose sites were bounded also carries a top-level locationSummary object — { totalLocations, matchedLocations, locationsTruncated, nearestRecruitingSiteAdded?, retrieveFullStudyWith } — absent when nothing was dropped; nearestRecruitingSiteAdded is present only when that extra site was added (the key keeps its name in the match-order fallback). Fetch a study's complete record and site list with clinicaltrials_get_study_record."
  5. Changed2 schema fields changed
    • changedInput schema / properties / locationLimit / description
      Previous value: -"Cap on the sites returned per candidate. Each candidate keeps only the sites matching the requested location at the narrowest level that matched (city, else state, else country), capped at this many; the rest of the study's registered sites are omitted. The cap governs those matched sites — when none of them is recruiting, the candidate's nearest recruiting site is added on top of it, so a candidate can carry one site more than this. Raise it to see more nearby sites, or fetch the complete site list with clinicaltrials_get_study_record. Each candidate reports totalLocations / matchedLocations / locationsTruncated / nearestRecruitingSiteAdded in locationSummary only when the bound actually dropped sites."New value: +"Cap on the sites returned per candidate. Each candidate keeps only the sites matching the requested location at the narrowest level that matched (city, else state, else country), capped at this many; the rest of the study's registered sites are omitted. The cap governs those matched sites — when none of them is recruiting, one recruiting site is added on top of it (the nearest to any matched site, measured before this cap, when coordinates allow — in the requested country whenever a site there recruits), so a candidate can carry one site more than this. Raise it to see more nearby sites, or fetch the complete site list with clinicaltrials_get_study_record. Each candidate reports totalLocations / matchedLocations / locationsTruncated / nearestRecruitingSiteAdded in locationSummary only when the bound actually dropped sites."
    • changedOutput schema / properties / studies / description
      Previous value: -"Matching studies with eligibility and location fields. Each candidate's protocolSection.contactsLocationsModule.locations is BOUNDED to the sites matching the requested location (capped at locationLimit) plus, when none of those is recruiting, the candidate's nearest recruiting site — not the study's full registered site list. A candidate whose sites were bounded also carries a top-level locationSummary object — { totalLocations, matchedLocations, locationsTruncated, nearestRecruitingSiteAdded?, retrieveFullStudyWith } — absent when nothing was dropped; nearestRecruitingSiteAdded is present only when that extra site was added. Fetch a study's complete record and site list with clinicaltrials_get_study_record."New value: +"Matching studies with eligibility and location fields. Each candidate's protocolSection.contactsLocationsModule.locations is BOUNDED to the sites matching the requested location (capped at locationLimit) plus, when none of those is recruiting, one added recruiting site — not the study's full registered site list. The added site is the one nearest any matched site by published coordinates, taken from the requested country whenever a site there recruits, and carries distanceMi (miles to that nearest matched site); when the matched or recruiting sites publish no coordinates it is the first in match order and carries no distanceMi. A candidate whose sites were bounded also carries a top-level locationSummary object — { totalLocations, matchedLocations, locationsTruncated, nearestRecruitingSiteAdded?, retrieveFullStudyWith } — absent when nothing was dropped; nearestRecruitingSiteAdded is present only when that extra site was added (the key keeps its name in the match-order fallback). Fetch a study's complete record and site list with clinicaltrials_get_study_record."
  6. Changed1 schema field changed
    • changedOutput schema / properties / searchCriteria / properties / location / description
      Previous value: -"The exact queryLocn string sent upstream (city/state/country joined). Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."New value: +"The exact queryLocn string sent upstream (city/state/country, multi-word components quoted, AND-joined). Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."
  7. Changed7 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / location / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "studies",
      +      "searchCriteria",
      +      "funnel"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode. Declared by this tool: `blank_value`: A parameter was supplied with a blank, whitespace-only, or empty-list value. `rate_limited`: ClinicalTrials.gov returned 429 after retry budget exhausted. Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "blank_value",
      +            "rate_limited"
      +          ],
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "studies",
      -  "searchCriteria",
      -  "funnel"
      -]
  8. Changed2 schema fields changed
    • addedInput schema / properties / locationLimit
      Added value: +{
      +  "default": 10,
      +  "description": "Cap on the sites returned per candidate. Each candidate keeps only the sites matching the requested location at the narrowest level that matched (city, else state, else country), capped at this many; the rest of the study's registered sites are omitted. The cap governs those matched sites — when none of them is recruiting, the candidate's nearest recruiting site is added on top of it, so a candidate can carry one site more than this. Raise it to see more nearby sites, or fetch the complete site list with clinicaltrials_get_study_record. Each candidate reports totalLocations / matchedLocations / locationsTruncated / nearestRecruitingSiteAdded in locationSummary only when the bound actually dropped sites.",
      +  "maximum": 500,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedOutput schema / properties / studies / description
      Previous value: -"Matching studies with eligibility and location fields."New value: +"Matching studies with eligibility and location fields. Each candidate's protocolSection.contactsLocationsModule.locations is BOUNDED to the sites matching the requested location (capped at locationLimit) plus, when none of those is recruiting, the candidate's nearest recruiting site — not the study's full registered site list. A candidate whose sites were bounded also carries a top-level locationSummary object — { totalLocations, matchedLocations, locationsTruncated, nearestRecruitingSiteAdded?, retrieveFullStudyWith } — absent when nothing was dropped; nearestRecruitingSiteAdded is present only when that extra site was added. Fetch a study's complete record and site list with clinicaltrials_get_study_record."
  9. Changed1 schema field changed
    • removedInput schema / properties / conditions / minItems
      Removed value: -1
  10. Changed5 schema fields changed
    • changedOutput schema / properties / searchCriteria / description
      Previous value: -"Normalized search criteria applied to this eligibility query."New value: +"Normalized search criteria applied to this eligibility query, including the exact upstream query strings needed to reproduce the full match set via clinicaltrials_search_studies (replay with includeUnknownEnrollment=true, which find_eligible always sets)."
    • addedOutput schema / properties / searchCriteria / properties / advancedFilter
      Added value: +{
      +  "description": "The exact AREA[] advancedFilter (age range, plus sex/healthy-volunteer when constrained) sent upstream. Pass as advancedFilter to clinicaltrials_search_studies to reproduce the demographic constraints.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / searchCriteria / properties / conditionQuery
      Added value: +{
      +  "description": "The exact queryCond string sent upstream (multi-word terms quoted, OR-joined). Pass as conditionQuery to clinicaltrials_search_studies to reproduce the full match set beyond the maxResults cap.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / searchCriteria / properties / location / description
      Previous value: -"Location searched."New value: +"The exact queryLocn string sent upstream (city/state/country joined). Pass as locationQuery to clinicaltrials_search_studies to reproduce the location filter beyond the maxResults cap."
    • addedOutput schema / properties / searchCriteria / properties / statusFilter
      Added value: +{
      +  "description": "The status filter applied ([\"RECRUITING\"] when recruitingOnly). Pass as statusFilter to clinicaltrials_search_studies. Absent when recruitingOnly is false.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  11. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]. Plain words plus AND/OR/NOT. `[ ]` are reserved; `( )` group sub-expressions when matched; `,` acts as AND."New value: +"Medical conditions or diagnoses, e.g. [\"Type 2 Diabetes\", \"Hypertension\"]. Each entry is matched as a condition (multi-word entries match as a phrase); multiple entries are combined with OR, so studies for any listed condition qualify. Returned studies are re-ranked so those whose own condition list names a requested condition rank above tangential matches the upstream fuzzy search pulls in via the MeSH umbrella."
  12. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]. Plain words only — reserved chars `[ ] ( ) ,` inside an entry will fail."New value: +"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]. Plain words plus AND/OR/NOT. `[ ]` are reserved; `( )` group sub-expressions when matched; `,` acts as AND."
  13. Changed4 schema fields changed
    • changedOutput schema / properties / funnel / description
      Previous value: -"Match counts at each filter stage. Diagnoses where the funnel collapsed on sparse results — e.g., conditionMatched=298 but demographicsMatched=2 means age/sex/status are the constraint."New value: +"Match counts at each filter stage. Shows where the funnel collapsed — e.g., conditionMatched=298 but demographicsMatched=2 means age/sex/status are the constraint."
    • removedOutput schema / properties / noMatchHints
      Removed value: -{
      -  "description": "Hints when no studies match, with suggestions to broaden the search.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • addedOutput schema / properties / notice
      Added value: +{
      +  "description": "Recovery guidance when no studies matched — identifies which filter stage collapsed and suggests how to broaden. Absent when results are returned.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / searchCriteria / description
      Previous value: -"Search criteria used."New value: +"Normalized search criteria applied to this eligibility query."
  14. Changed2 schema fields changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]. Plain words only — brackets, parentheses, and commas inside an entry will trip the upstream Essie parser."New value: +"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]. Plain words only — reserved chars `[ ] ( ) ,` inside an entry will fail."
    • changedInput schema / properties / location / description
      Previous value: -"Patient location."New value: +"Patient location as `{ country (required), state?, city? }`. Country is required; state/city narrow the match. For radius-based geographic search, use clinicaltrials_search_studies with geoFilter."
  15. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]."New value: +"Medical conditions or diagnoses. E.g., [\"Type 2 Diabetes\", \"Hypertension\"]. Plain words only — brackets, parentheses, and commas inside an entry will trip the upstream Essie parser."
  16. Changed2 schema fields changed
    • addedOutput schema / properties / funnel
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Match counts at each filter stage. Diagnoses where the funnel collapsed on sparse results — e.g., conditionMatched=298 but demographicsMatched=2 means age/sex/status are the constraint.",
      +  "properties": {
      +    "conditionMatched": {
      +      "description": "Studies matching the condition query alone (broadest stage).",
      +      "type": "number"
      +    },
      +    "demographicsMatched": {
      +      "description": "Studies matching the full filter set (condition + location + age/sex + status). Equal to totalCount.",
      +      "type": "number"
      +    },
      +    "locationMatched": {
      +      "description": "Studies matching condition + location — diagnoses geographic narrowing.",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "conditionMatched",
      +    "locationMatched",
      +    "demographicsMatched"
      +  ],
      +  "type": "object"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "studies",
      -  "searchCriteria"
      -]New value: +[
      +  "studies",
      +  "searchCriteria",
      +  "funnel"
      +]
  17. Changed2 schema fields changed
    • changedInput schema / properties / sex / description
      Previous value: -"Patient's biological sex. Use 'All' to include studies regardless of sex restrictions."New value: +"Patient's biological sex. Use 'ALL' to include studies regardless of sex restrictions."
    • changedInput schema / properties / sex / enum
      Previous value: -[
      -  "Female",
      -  "Male",
      -  "All"
      -]New value: +[
      +  "FEMALE",
      +  "MALE",
      +  "ALL"
      +]
  18. Changed1 schema field changed
    • changedInput schema / properties / sex / description
      Previous value: -"Biological sex."New value: +"Patient's biological sex. Use 'All' to include studies regardless of sex restrictions."
  19. First observed

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnly/idempotent annotations already covering safety, the description adds substantial non-obvious behavior: fuzzy condition pulling via the MeSH umbrella, re-ranking to surface exact-condition matches, per-candidate site truncation rather than the full registry site list, and the rule that one recruiting site is injected on top of locationLimit when all matched sites are closed. These are things an agent could not infer from annotations or schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and caveats are front-loaded, but the recruiting-site fallback heuristic is described at excessive depth (nearest by published coordinates, requested-country precedence, distanceMi, first-in-match-order fallback), which is largely restated in the locationLimit schema text. The final sentence pointing to clinicaltrials_get_study_record is a useful close, but the middle is denser than needed for selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter, nested-object, read-only search tool with an output schema, the description covers the essential risks: criteria are not evaluated, condition matching is fuzzy, and site lists are truncated. Return-value shape is correctly left to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description adds cross-parameter semantics the schema states less prominently — that each candidate carries only location-matched sites capped by locationLimit, and that an extra recruiting site can make a result exceed the cap. It does not add much beyond the schema for age/sex/conditions, which are already richly documented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Find candidate clinical trials for a patient profile") and immediately delimits scope: it matches only on age, sex, location, recruitment status and fuzzy condition search, not eligibility criteria. This clearly separates it from clinicaltrials_search_studies (keyword/geo search) and clinicaltrials_get_study_record (full record).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it (patient profile with age/sex/conditions/location), what it does not do (inclusion/exclusion criteria unchecked), and routes the agent to clinicaltrials_get_study_record to review criteria before treating a result as a match. The schema also routes radius-based search to clinicaltrials_search_studies with geoFilter, so the alternative path is covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.