Skip to main content
Glama
clinicaltrialsgov-mcp-server

clinicaltrialsgov-mcp-server

by cyanheads

Clinicaltrials Get Field Values

clinicaltrials_get_field_values
Read-onlyIdempotent

Discover valid values and study counts for ClinicalTrials.gov fields such as OverallStatus, Phase, or LeadSponsorClass to explore filter options before building a search query.

Instructions

Discover valid values for ClinicalTrials.gov fields with study counts per value. Use to explore available filter options before building a search — e.g., valid OverallStatus, Phase, InterventionType, StudyType, or LeadSponsorClass values.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "fields": "<fields>"
    },
    "name": "clinicaltrials_get_field_values"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldsYesPascalCase leaf piece name(s) to get value statistics for — an empty list is rejected, not treated as "every field". Index-only pieces count too (NumLocations, StudyFirstPostYear — listed by clinicaltrials_get_field_definitions in drill mode with includeIndexedOnly), as do legacy alt names such as OVERALL-STATUS; a search area such as ConditionSearch does not. A group of fields (LeadSponsor, ConditionMesh) is refused with its leaf pieces named (LeadSponsorName, ConditionMeshTerm), and a full path as clinicaltrials_get_field_definitions prints it ("protocolSection.statusModule.overallStatus") is read as its piece name. A comma- or pipe-joined string ("Phase,StudyType") is split into separate names. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
noticeNoPresent when a longest value was cut to a preview — names, for each such field, the clinicaltrials_search_studies arguments that return its full text — or when multiValued could not be determined for a field, which then carries no multiValued flag and may be repeated.
fieldStatsNoOne entry per requested field: canonical path, PascalCase piece name, data type, and the statistics variant that type carries — top values with study counts plus unique/longest for ENUM/STRING, trueCount/falseCount for BOOLEAN, min/max/avg for INTEGER/NUMBER, min/max/formats for DATE.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.11.3
    • changedInput schema / properties / fields / description
      Previous value: -"PascalCase leaf piece name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". A group of fields (LeadSponsor, ConditionMesh) is refused with its leaf pieces named (LeadSponsorName, ConditionMeshTerm), and a full path as clinicaltrials_get_field_definitions prints it (\"protocolSection.statusModule.overallStatus\") is read as its piece name. A comma- or pipe-joined string (\"Phase,StudyType\") is split into separate names. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."New value: +"PascalCase leaf piece name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". Index-only pieces count too (NumLocations, StudyFirstPostYear — listed by clinicaltrials_get_field_definitions in drill mode with includeIndexedOnly), as do legacy alt names such as OVERALL-STATUS; a search area such as ConditionSearch does not. A group of fields (LeadSponsor, ConditionMesh) is refused with its leaf pieces named (LeadSponsorName, ConditionMeshTerm), and a full path as clinicaltrials_get_field_definitions prints it (\"protocolSection.statusModule.overallStatus\") is read as its piece name. A comma- or pipe-joined string (\"Phase,StudyType\") is split into separate names. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."
    • 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. `field_invalid`: A requested name is not a field, names a group of fields such as LeadSponsor or ConditionMesh instead of its leaf pieces, or names a leaf whose type ClinicalTrials.gov does not count, such as LocationGeoPoint. `request_too_long`: The fields list makes the request URL longer than ClinicalTrials.gov accepts — a few hundred piece names in one call. `rate_limited`: ClinicalTrials.gov answered HTTP 429 on every attempt, or the call’s time budget ran out after a 429. `retry_deadline_exceeded`: ClinicalTrials.gov did not answer within the call’s time budget, which covers every request, retry, and wait the call makes. `upstream_timeout`: ClinicalTrials.gov answered HTTP 504 (gateway timeout) on every attempt. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `blank_value`: A parameter was supplied with a blank, whitespace-only, or empty-list value. `field_invalid`: A requested name is not a field (a record or index-only piece such as NumLocations, or an alt name of one; a search area such as ConditionSearch is not), names a group of fields such as LeadSponsor or ConditionMesh instead of its leaf pieces, or names a leaf whose type ClinicalTrials.gov does not count, such as LocationGeoPoint. `request_too_long`: The fields list makes the request URL longer than ClinicalTrials.gov accepts — a few hundred piece names in one call. `rate_limited`: ClinicalTrials.gov answered HTTP 429 on every attempt, or the call’s time budget ran out after a 429. `retry_deadline_exceeded`: ClinicalTrials.gov did not answer within the call’s time budget, which covers every request, retry, and wait the call makes. `upstream_timeout`: ClinicalTrials.gov answered HTTP 504 (gateway timeout) or 408 (request timeout), or sent no answer within the per-attempt timeout, on every attempt. `upstream_unavailable`: Every attempt failed on ClinicalTrials.gov’s side — HTTP 500, 502, or 503, a dropped connection or one the network gave up opening, or a 200 body that is not the JSON the route serves (an HTML page, unparseable text, the wrong shape) — or it answered with another 5xx, such as 505, or the connection was refused or its host name did not resolve, none of which is retried. `upstream_rejected`: ClinicalTrials.gov refused the request with a status its API does not use for a bad query — HTTP 501, a 3xx, or a 4xx such as 401, 403, or 410 — or answered with an HTML error page in place of its own 404. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "blank_value",
      -  "field_invalid",
      -  "request_too_long",
      -  "rate_limited",
      -  "retry_deadline_exceeded",
      -  "upstream_timeout"
      -]New value: +[
      +  "blank_value",
      +  "field_invalid",
      +  "request_too_long",
      +  "rate_limited",
      +  "retry_deadline_exceeded",
      +  "upstream_timeout",
      +  "upstream_unavailable",
      +  "upstream_rejected"
      +]
    • changedOutput schema / properties / fieldStats / items / properties / multiValued / description
      Previous value: -"True when the field is repeated — array-typed itself (Phase, Condition) or nested under a repeated object (LocationCountry, one per site) — so a study can carry several values and the per-value studiesCount buckets sum above the study total. Use to avoid computing a percentage against the corpus."New value: +"True when the field is repeated — array-typed itself (Phase, Condition) or nested under a repeated object (LocationCountry, one per site) — so a study can carry several values and the per-value studiesCount buckets sum above the study total. Use to avoid computing a percentage against the corpus. Absent for a single-valued field, and for any field the notice names as not determined."
    • changedOutput schema / properties / notice / description
      Previous value: -"Present when a longest value was cut to a preview — names, for each such field, the clinicaltrials_search_studies arguments that return its full text."New value: +"Present when a longest value was cut to a preview — names, for each such field, the clinicaltrials_search_studies arguments that return its full text — or when multiValued could not be determined for a field, which then carries no multiValued flag and may be repeated."
  2. Changed4 schema fields changedv2.11.2
    • changedInput schema / properties / fields / anyOf
      Previous value: -[
      -  {
      -    "description": "A single PascalCase field name.",
      -    "type": "string"
      -  },
      -  {
      -    "description": "Multiple PascalCase field names (at least one required).",
      -    "items": {
      -      "type": "string"
      -    },
      -    "type": "array"
      -  }
      -]New value: +[
      +  {
      +    "description": "A single PascalCase leaf piece name.",
      +    "type": "string"
      +  },
      +  {
      +    "description": "Multiple PascalCase leaf piece names (at least one required).",
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  }
      +]
    • changedInput schema / properties / fields / description
      Previous value: -"PascalCase field name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". A comma- or pipe-joined string (\"Phase,StudyType\") is split into separate names. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."New value: +"PascalCase leaf piece name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". A group of fields (LeadSponsor, ConditionMesh) is refused with its leaf pieces named (LeadSponsorName, ConditionMeshTerm), and a full path as clinicaltrials_get_field_definitions prints it (\"protocolSection.statusModule.overallStatus\") is read as its piece name. A comma- or pipe-joined string (\"Phase,StudyType\") is split into separate names. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."
    • 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. `field_invalid`: A requested field name is not a valid PascalCase piece name. `request_too_long`: The fields list makes the request URL longer than ClinicalTrials.gov accepts — a few hundred piece names in one call. `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 parameter was supplied with a blank, whitespace-only, or empty-list value. `field_invalid`: A requested name is not a field, names a group of fields such as LeadSponsor or ConditionMesh instead of its leaf pieces, or names a leaf whose type ClinicalTrials.gov does not count, such as LocationGeoPoint. `request_too_long`: The fields list makes the request URL longer than ClinicalTrials.gov accepts — a few hundred piece names in one call. `rate_limited`: ClinicalTrials.gov answered HTTP 429 on every attempt, or the call’s time budget ran out after a 429. `retry_deadline_exceeded`: ClinicalTrials.gov did not answer within the call’s time budget, which covers every request, retry, and wait the call makes. `upstream_timeout`: ClinicalTrials.gov answered HTTP 504 (gateway timeout) on every attempt. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "blank_value",
      -  "field_invalid",
      -  "request_too_long",
      -  "rate_limited"
      -]New value: +[
      +  "blank_value",
      +  "field_invalid",
      +  "request_too_long",
      +  "rate_limited",
      +  "retry_deadline_exceeded",
      +  "upstream_timeout"
      +]
  3. Changed2 schema fields changedv2.11.0
    • 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. `field_invalid`: A requested field name is not a valid PascalCase piece name. `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 parameter was supplied with a blank, whitespace-only, or empty-list value. `field_invalid`: A requested field name is not a valid PascalCase piece name. `request_too_long`: The fields list makes the request URL longer than ClinicalTrials.gov accepts — a few hundred piece names 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",
      -  "field_invalid",
      -  "rate_limited"
      -]New value: +[
      +  "blank_value",
      +  "field_invalid",
      +  "request_too_long",
      +  "rate_limited"
      +]
  4. Changed6 schema fields changedv2.10.1
    • changedOutput schema / properties / fieldStats / items / properties / longest / properties / length / description
      Previous value: -"Its length in characters."New value: +"Full length of the recorded value in characters, even when truncated."
    • addedOutput schema / properties / fieldStats / items / properties / longest / properties / truncated
      Added value: +{
      +  "const": true,
      +  "description": "True when value is a preview of at most 2,000 characters; absent when value is whole. The notice names the clinicaltrials_search_studies call that returns the full text.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / fieldStats / items / properties / longest / properties / value / description
      Previous value: -"The longest recorded value."New value: +"The longest recorded value — when truncated is true, only a prefix of at most 2,000 characters (1,999 when the cut would split a surrogate pair)."
    • changedOutput schema / properties / fieldStats / items / properties / uniqueValuesCount / description
      Previous value: -"Number of distinct values."New value: +"Number of distinct values, as ClinicalTrials.gov reports it. Free-text STRING fields it does not count (DetailedDescription, EligibilityCriteria) report 0 here alongside uniqueValuesCounted: false — that 0 is not a count. A 0 without the flag means no recorded values."
    • addedOutput schema / properties / fieldStats / items / properties / uniqueValuesCounted
      Added value: +{
      +  "const": false,
      +  "description": "False when ClinicalTrials.gov did not count distinct values for this field, so the uniqueValuesCount of 0 is not a real count — the field has recorded values (see longest) but no topValues. Absent otherwise.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / notice
      Added value: +{
      +  "description": "Present when a longest value was cut to a preview — names, for each such field, the clinicaltrials_search_studies arguments that return its full text.",
      +  "type": "string"
      +}
  5. Changed1 schema field changedv2.10.0
    • changedInput schema / properties / fields / description
      Previous value: -"PascalCase field name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."New value: +"PascalCase field name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". A comma- or pipe-joined string (\"Phase,StudyType\") is split into separate names. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."
  6. Changed7 schema fields changedv2.9.6
    • changedOutput schema / properties / fieldStats / description
      Previous value: -"One entry per requested field: canonical path, PascalCase piece name, data type, missing/unique counts, and top values with study counts (or trueCount/falseCount for BOOLEAN fields)."New value: +"One entry per requested field: canonical path, PascalCase piece name, data type, and the statistics variant that type carries — top values with study counts plus unique/longest for ENUM/STRING, trueCount/falseCount for BOOLEAN, min/max/avg for INTEGER/NUMBER, min/max/formats for DATE."
    • addedOutput schema / properties / fieldStats / items / properties / avg
      Added value: +{
      +  "description": "Mean of the recorded values. Present for INTEGER/NUMBER fields.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / fieldStats / items / properties / formats
      Added value: +{
      +  "description": "Date patterns this field is recorded in. Present for DATE fields; more than one means the field mixes precisions across studies.",
      +  "items": {
      +    "description": "A date pattern, e.g. \"yyyy-MM-dd\".",
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / fieldStats / items / properties / longest
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Longest recorded value with its length and a study carrying it. Present for STRING fields only.",
      +  "properties": {
      +    "length": {
      +      "description": "Its length in characters.",
      +      "type": "number"
      +    },
      +    "nctId": {
      +      "description": "NCT ID of a study carrying it.",
      +      "type": "string"
      +    },
      +    "value": {
      +      "description": "The longest recorded value.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "value",
      +    "length",
      +    "nctId"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / fieldStats / items / properties / max
      Added value: +{
      +  "anyOf": [
      +    {
      +      "description": "Largest value of an INTEGER/NUMBER field.",
      +      "type": "number"
      +    },
      +    {
      +      "description": "Latest value of a DATE field, at the precision recorded.",
      +      "type": "string"
      +    }
      +  ],
      +  "description": "Largest recorded value — a number for INTEGER/NUMBER, a date string for DATE."
      +}
    • addedOutput schema / properties / fieldStats / items / properties / min
      Added value: +{
      +  "anyOf": [
      +    {
      +      "description": "Smallest value of an INTEGER/NUMBER field.",
      +      "type": "number"
      +    },
      +    {
      +      "description": "Earliest value of a DATE field, at the precision recorded — a partial date such as \"1900-01\" stays partial.",
      +      "type": "string"
      +    }
      +  ],
      +  "description": "Smallest recorded value — a number for INTEGER/NUMBER, a date string for DATE."
      +}
    • changedOutput schema / properties / fieldStats / items / properties / multiValued / description
      Previous value: -"True when the field is array-typed (a study can carry several values, e.g. Phase, Condition), so the per-value studiesCount buckets sum above the study total. Use to avoid computing a percentage against the corpus."New value: +"True when the field is repeated — array-typed itself (Phase, Condition) or nested under a repeated object (LocationCountry, one per site) — so a study can carry several values and the per-value studiesCount buckets sum above the study total. Use to avoid computing a percentage against the corpus."
  7. Changed6 schema fields changedv2.9.2
    • 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
    • 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": [
      +      "fieldStats"
      +    ]
      +  },
      +  {
      +    "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. `field_invalid`: A requested field name is not a valid PascalCase piece name. `rate_limited`: ClinicalTrials.gov returned 429 after retry budget exhausted. Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "blank_value",
      +            "field_invalid",
      +            "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: -[
      -  "fieldStats"
      -]
  8. Changed2 schema fields changedv2.9.1
    • changedInput schema / properties / fields / anyOf
      Previous value: -[
      -  {
      -    "description": "A single PascalCase field name.",
      -    "type": "string"
      -  },
      -  {
      -    "description": "Multiple PascalCase field names (at least one required).",
      -    "items": {
      -      "type": "string"
      -    },
      -    "minItems": 1,
      -    "type": "array"
      -  }
      -]New value: +[
      +  {
      +    "description": "A single PascalCase field name.",
      +    "type": "string"
      +  },
      +  {
      +    "description": "Multiple PascalCase field names (at least one required).",
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  }
      +]
    • changedInput schema / properties / fields / description
      Previous value: -"PascalCase field name(s) to get value statistics for. Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."New value: +"PascalCase field name(s) to get value statistics for — an empty list is rejected, not treated as \"every field\". Examples: OverallStatus, Phase, StudyType, Sex, LeadSponsorClass. Use clinicaltrials_get_field_definitions with a query to find more field names."
  9. Changed3 schema fields changedv2.7.1
    • changedInput schema / properties / fields / anyOf
      Previous value: -[
      -  {
      -    "description": "A single PascalCase field name.",
      -    "type": "string"
      -  },
      -  {
      -    "description": "Multiple PascalCase field names.",
      -    "items": {
      -      "type": "string"
      -    },
      -    "type": "array"
      -  }
      -]New value: +[
      +  {
      +    "description": "A single PascalCase field name.",
      +    "type": "string"
      +  },
      +  {
      +    "description": "Multiple PascalCase field names (at least one required).",
      +    "items": {
      +      "type": "string"
      +    },
      +    "minItems": 1,
      +    "type": "array"
      +  }
      +]
    • addedOutput schema / properties / fieldStats / items / properties / multiValued
      Added value: +{
      +  "description": "True when the field is array-typed (a study can carry several values, e.g. Phase, Condition), so the per-value studiesCount buckets sum above the study total. Use to avoid computing a percentage against the corpus.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / fieldStats / items / properties / topValues / description
      Previous value: -"Values ranked by frequency (capped at 250 by the API). Present for ENUM/STRING fields."New value: +"Values ranked by frequency (capped at 250 by the API). Present for ENUM/STRING fields. When multiValued is true, studiesCount sums can exceed the study total."
  10. Addedv2.5.1
  11. Removedv2.4.12
  12. Addedv2.0.6

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds that results include study counts per value, which is modest extra context. It says nothing about cost or latency of an aggregation over the full corpus, nor about how invalid or grouped field names are handled (that is only in the schema).

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

Conciseness5/5

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

Two sentences, front-loaded with the core action and followed by the usage condition. No filler, no restatement of the title, and every clause carries information.

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

Completeness4/5

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

With one required parameter, full schema coverage, annotations, and an output schema, the description only needs to establish purpose and when to reach for it — both are done. The remaining gap is the absence of any pointer to the companion tool for discovering field names, which the schema mentions but the description does not.

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

Parameters3/5

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

Schema description coverage is 100% and the parameter documentation is unusually thorough, so the baseline is 3. The description's list of example fields (OverallStatus, Phase, InterventionType, StudyType, LeadSponsorClass) largely duplicates examples already present in the schema. It adds little semantic meaning beyond what the parameter definition provides.

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

Purpose4/5

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

States a specific verb and resource: 'Discover valid values for ClinicalTrials.gov fields with study counts per value.' An agent can immediately tell this is a value-enumeration tool, distinct from retrieving a study record or searching. It does not name the sibling that supplies field names (clinicaltrials_get_field_definitions), so differentiation is implied rather than explicit.

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

Usage Guidelines4/5

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

Gives a clear usage context: 'Use to explore available filter options before building a search,' which tells the agent this is a discovery/preparation step. It does not state when-not to use it or name an alternative tool, so it stops short of full routing guidance.

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