Skip to main content
Glama
cyanheads

pubmed-mcp-server

by cyanheads

Pubmed Search Articles

pubmed_search_articles
Read-only

Search PubMed using full query syntax and filters like author, journal, MeSH, date range, and species. Returns PMIDs with optional summaries and supports pagination for large result sets.

Instructions

Search PubMed with full query syntax, filters, and date ranges. Returns PMIDs and optional brief summaries. Supports field-specific filters (author, journal, MeSH terms), common filters (language, species, free full text), and pagination via offset for paging through large result sets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoSort order: relevance (default), pub_date (newest first), author, or journalrelevance
queryYesPubMed search query (supports full NCBI syntax). Must carry a search term: a value that is blank once markup, bracketed field tags (`[pdat]`), parentheses, and invisible characters such as a zero-width space are disregarded is rejected rather than sent to PubMed.
authorNoFilter by author name (e.g. "Smith J"). An empty string applies no filter; a value of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected.
offsetNoResult offset for pagination (0-based). PubMed serves at most the first 9999 records of a result set, so this caps at 9998; narrow the query or add filters to reach anything beyond it.
journalNoFilter by journal name. An empty string applies no filter; a value of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected.
speciesNoFilter by species
languageNoFilter by language (e.g. "english"). An empty string applies no filter; a value of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected.
dateRangeNoFilter by date range. The filter is applied only when both `minDate` and `maxDate` are non-empty; either one empty disables the entire date range. A partial date covers its whole year or month, and a range whose `minDate` falls after its `maxDate` is rejected: `2024/06` to `2024` is valid, `2024/07` to `2024/06/30` is not.
meshTermsNoFilter by MeSH terms. Multiple terms are AND'd — all must match. Empty strings are skipped; an element of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected.
maxResultsNoMaximum results to return
hasAbstractNoOnly include articles with abstracts
freeFullTextNoOnly include free full text articles
summaryCountNoFetch brief summaries for top N results (0 = PMIDs only). Above the 50 cap, pass the remaining PMIDs to pubmed_fetch_articles.
publicationTypesNoFilter by publication type (e.g. "Review", "Clinical Trial", "Meta-Analysis"). Multiple values are OR'd — any match qualifies. Empty strings are skipped; an element of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
pmidsNoPubMed IDs
queryNoOriginal query
noticeNoOptional guidance when the result set does not reflect what was asked for — a field tag PubMed ignored, a phrase it matched nothing for, a dateRange dropped for having one bound, no matches at all, or paging past the end. Absent when nothing applies.
offsetNoResult offset used
searchUrlNoPubMed search URL
summariesNoBrief summaries (empty array when summaryCount is 0)
totalCountNoTotal matching articles
appliedFiltersNoNormalized filter values that were applied to the PubMed query
effectiveQueryNoSanitized query sent to PubMed after applying all active filters

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv2.10.19
    • changedInput schema / properties / author / description
      Previous value: -"Filter by author name (e.g. \"Smith J\")"New value: +"Filter by author name (e.g. \"Smith J\"). An empty string applies no filter; a value of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected."
    • changedInput schema / properties / dateRange / description
      Previous value: -"Filter by date range. The filter is applied only when both `minDate` and `maxDate` are non-empty; either one empty disables the entire date range."New value: +"Filter by date range. The filter is applied only when both `minDate` and `maxDate` are non-empty; either one empty disables the entire date range. A partial date covers its whole year or month, and a range whose `minDate` falls after its `maxDate` is rejected: `2024/06` to `2024` is valid, `2024/07` to `2024/06/30` is not."
    • changedInput schema / properties / dateRange / properties / maxDate / description
      Previous value: -"End date (YYYY/MM/DD, YYYY/MM, or YYYY); empty string disables this bound"New value: +"End date (YYYY/MM/DD, YYYY/MM, or YYYY); empty string disables this bound. Must be a real calendar date — `2023/02/29` is rejected."
    • changedInput schema / properties / dateRange / properties / minDate / description
      Previous value: -"Start date (YYYY/MM/DD, YYYY/MM, or YYYY); empty string disables this bound"New value: +"Start date (YYYY/MM/DD, YYYY/MM, or YYYY); empty string disables this bound. Must be a real calendar date — `2023/02/29` is rejected."
    • changedInput schema / properties / journal / description
      Previous value: -"Filter by journal name"New value: +"Filter by journal name. An empty string applies no filter; a value of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected."
    • changedInput schema / properties / language / description
      Previous value: -"Filter by language (e.g. \"english\")"New value: +"Filter by language (e.g. \"english\"). An empty string applies no filter; a value of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected."
    • changedInput schema / properties / meshTerms / description
      Previous value: -"Filter by MeSH terms. Multiple terms are AND'd — all must match."New value: +"Filter by MeSH terms. Multiple terms are AND'd — all must match. Empty strings are skipped; an element of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected."
    • changedInput schema / properties / publicationTypes / description
      Previous value: -"Filter by publication type (e.g. \"Review\", \"Clinical Trial\", \"Meta-Analysis\"). Multiple values are OR'd — any match qualifies."New value: +"Filter by publication type (e.g. \"Review\", \"Clinical Trial\", \"Meta-Analysis\"). Multiple values are OR'd — any match qualifies. Empty strings are skipped; an element of only whitespace, invisible characters, markup, parentheses, brackets, or double quotes is rejected."
    • changedInput schema / properties / query / description
      Previous value: -"PubMed search query (supports full NCBI syntax). Must carry a search term: a value that is blank once markup, bracketed field tags (`[pdat]`), and parentheses are removed is rejected rather than sent to PubMed as an empty term."New value: +"PubMed search query (supports full NCBI syntax). Must carry a search term: a value that is blank once markup, bracketed field tags (`[pdat]`), parentheses, and invisible characters such as a zero-width space are disregarded is rejected rather than sent to PubMed."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `queue_full`: The local NCBI request queue shed the call — the queue is full, or the call cannot start before its total deadline (for example behind the cooldown that follows an NCBI 429). `ncbi_unreachable`: NCBI E-utilities is unreachable after all retry attempts. `ncbi_deadline_exceeded`: Total request deadline expired before NCBI returned a response. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). `blank_query`: The query holds no search term once whitespace, and anything the tool strips before searching, are removed — so NCBI would receive a blank term. pubmed_search_articles strips markup, bracketed field tags, and parentheses, so a bare field tag such as `[pdat]` or empty parentheses `()` count as blank there. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `queue_full`: The local NCBI request queue shed the call — the queue is full, or the call cannot start before its total deadline (for example behind the cooldown that follows an NCBI 429). `ncbi_unreachable`: NCBI E-utilities failed on every attempt the retry budget allowed — retries ran out, or the next backoff would overrun the total deadline. `ncbi_rate_limited`: NCBI answered HTTP 429 (too many requests) and the call stopped on it — retries ran out, the next backoff would overrun the total deadline, or the Retry-After NCBI named outlasts the time left or the 30-second backoff cap. `ncbi_deadline_exceeded`: The total NCBI request deadline expired before NCBI answered successfully — mid-request, while queued, or during a retry backoff. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). `blank_query`: The query contains no search term: nothing is left once whitespace and invisible characters such as a zero-width space are disregarded. pubmed_search_articles and pubmed_europepmc_search first decode HTML entities and also disregard markup and parentheses, so `()`, `<b></b>`, and `&nbsp;` hold no term there; pubmed_search_articles also disregards bracketed field tags such as `[pdat]`. `invalid_date_range`: A `dateRange` bound is not a real calendar date — a month outside 01–12, day 00, or a day past the end of its month such as `2023/02/29` — or `minDate` falls after `maxDate` once PubMed expands each partial date: `minDate` from the start of its year or month, `maxDate` to the end. `blank_filter`: An `author`, `journal`, or `language` value, or a `publicationTypes` or `meshTerms` element, holds no term once markup is removed and HTML entities are decoded — only whitespace, invisible characters such as a zero-width space, parentheses, brackets, or double quotes are left, as in `()` or `\"\"` — so its field clause would carry no term. An exactly-empty string is not blank here; it sets no filter. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "queue_full",
      -  "ncbi_unreachable",
      -  "ncbi_deadline_exceeded",
      -  "ncbi_invalid_response",
      -  "ncbi_resource_not_found",
      -  "blank_query"
      -]New value: +[
      +  "queue_full",
      +  "ncbi_unreachable",
      +  "ncbi_rate_limited",
      +  "ncbi_deadline_exceeded",
      +  "ncbi_invalid_response",
      +  "ncbi_resource_not_found",
      +  "blank_query",
      +  "invalid_date_range",
      +  "blank_filter"
      +]
  2. Changed3 schema fields changedv2.10.18
    • changedInput schema / properties / query / description
      Previous value: -"PubMed search query (supports full NCBI syntax). Must carry a search term: a value that is blank once markup is stripped is rejected rather than sent to PubMed as an empty term."New value: +"PubMed search query (supports full NCBI syntax). Must carry a search term: a value that is blank once markup, bracketed field tags (`[pdat]`), and parentheses are removed is rejected rather than sent to PubMed as an empty term."
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "not": {
      -      "required": [
      -        "error"
      -      ]
      -    },
      -    "required": [
      -      "query",
      -      "offset",
      -      "pmids",
      -      "summaries",
      -      "searchUrl",
      -      "effectiveQuery",
      -      "totalCount",
      -      "appliedFilters"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "error"
      -    ]
      -  }
      -]New value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "query",
      +      "offset",
      +      "pmids",
      +      "summaries",
      +      "searchUrl",
      +      "totalCount",
      +      "effectiveQuery",
      +      "appliedFilters"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `queue_full`: Local NCBI request queue is at capacity. `ncbi_unreachable`: NCBI E-utilities is unreachable after all retry attempts. `ncbi_deadline_exceeded`: Total request deadline expired before NCBI returned a response. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). `blank_query`: The query holds no search term once whitespace, and any markup the tool strips first, are removed — so NCBI would receive a blank term. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `queue_full`: The local NCBI request queue shed the call — the queue is full, or the call cannot start before its total deadline (for example behind the cooldown that follows an NCBI 429). `ncbi_unreachable`: NCBI E-utilities is unreachable after all retry attempts. `ncbi_deadline_exceeded`: Total request deadline expired before NCBI returned a response. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). `blank_query`: The query holds no search term once whitespace, and anything the tool strips before searching, are removed — so NCBI would receive a blank term. pubmed_search_articles strips markup, bracketed field tags, and parentheses, so a bare field tag such as `[pdat]` or empty parentheses `()` count as blank there. Other values are possible when a failure originates below the handler."
  3. Changed9 schema fields changedv2.10.12
    • changedInput schema / properties / query / description
      Previous value: -"PubMed search query (supports full NCBI syntax)"New value: +"PubMed search query (supports full NCBI syntax). Must carry a search term: a value that is blank once markup is stripped is rejected rather than sent to PubMed as an empty term."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `queue_full`: Local NCBI request queue is at capacity. `ncbi_unreachable`: NCBI E-utilities is unreachable after all retry attempts. `ncbi_deadline_exceeded`: Total request deadline expired before NCBI returned a response. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `queue_full`: Local NCBI request queue is at capacity. `ncbi_unreachable`: NCBI E-utilities is unreachable after all retry attempts. `ncbi_deadline_exceeded`: Total request deadline expired before NCBI returned a response. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). `blank_query`: The query holds no search term once whitespace, and any markup the tool strips first, are removed — so NCBI would receive a blank term. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "queue_full",
      -  "ncbi_unreachable",
      -  "ncbi_deadline_exceeded",
      -  "ncbi_invalid_response",
      -  "ncbi_resource_not_found"
      -]New value: +[
      +  "queue_full",
      +  "ncbi_unreachable",
      +  "ncbi_deadline_exceeded",
      +  "ncbi_invalid_response",
      +  "ncbi_resource_not_found",
      +  "blank_query"
      +]
    • changedOutput schema / properties / summaries / items / properties / authors / description
      Previous value: -"Formatted author string"New value: +"Formatted author string — the first three of the record's own authors, then \"et al.\". On an NCBI Bookshelf chapter these are the chapter's authors; the book's editors are reported separately in `editors`."
    • addedOutput schema / properties / summaries / items / properties / bookTitle
      Added value: +{
      +  "description": "Title of the book an NCBI Bookshelf record belongs to, e.g. \"GeneReviews(®)\". Present instead of `source` on a book record; absent on a journal article.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / summaries / items / properties / docType
      Added value: +{
      +  "description": "What PubMed classifies this record as: \"chapter\" or \"book\" for an NCBI Bookshelf record, \"citation\" for an ordinary journal article. Absent when PubMed supplies none.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / summaries / items / properties / editors
      Added value: +{
      +  "description": "Editors of the containing book, kept out of `authors` so they cannot displace the record's own authors. Absent on a journal article and on a book that credits no editors.",
      +  "items": {
      +    "description": "One editor, \"Surname Initials\" as ESummary renders it",
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / summaries / items / properties / publisherName
      Added value: +{
      +  "description": "Publisher of the book an NCBI Bookshelf record belongs to. Present only on a book record; absent on a journal article.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / summaries / items / properties / source / description
      Previous value: -"Journal source"New value: +"Journal the article appeared in. Absent on an NCBI Bookshelf record, which has no journal — its venue is in `bookTitle` and `publisherName` instead, and `docType` says which kind of record it is."
  4. Changed6 schema fields changedv2.10.4
    • 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": [
      +      "query",
      +      "offset",
      +      "pmids",
      +      "summaries",
      +      "searchUrl",
      +      "effectiveQuery",
      +      "totalCount",
      +      "appliedFilters"
      +    ]
      +  },
      +  {
      +    "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: `queue_full`: Local NCBI request queue is at capacity. `ncbi_unreachable`: NCBI E-utilities is unreachable after all retry attempts. `ncbi_deadline_exceeded`: Total request deadline expired before NCBI returned a response. `ncbi_invalid_response`: NCBI returned a body that could not be parsed (invalid XML/JSON). `ncbi_resource_not_found`: NCBI returned a structured \"not found\" error for the requested ID(s). Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "queue_full",
      +            "ncbi_unreachable",
      +            "ncbi_deadline_exceeded",
      +            "ncbi_invalid_response",
      +            "ncbi_resource_not_found"
      +          ],
      +          "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: -[
      -  "query",
      -  "offset",
      -  "pmids",
      -  "summaries",
      -  "searchUrl",
      -  "effectiveQuery",
      -  "totalCount",
      -  "appliedFilters"
      -]
  5. Changed5 schema fields changedv2.10.2
    • changedInput schema / properties / offset / description
      Previous value: -"Result offset for pagination (0-based)"New value: +"Result offset for pagination (0-based). PubMed serves at most the first 9999 records of a result set, so this caps at 9998; narrow the query or add filters to reach anything beyond it."
    • changedInput schema / properties / offset / maximum
      Previous value: -9007199254740991New value: +9998
    • changedInput schema / properties / summaryCount / description
      Previous value: -"Fetch brief summaries for top N results (0 = PMIDs only)"New value: +"Fetch brief summaries for top N results (0 = PMIDs only). Above the 50 cap, pass the remaining PMIDs to pubmed_fetch_articles."
    • changedOutput schema / properties / notice / description
      Previous value: -"Optional guidance when results are empty or paging overshot — e.g. how to broaden filters or reset offset. Absent on successful result pages."New value: +"Optional guidance when the result set does not reflect what was asked for — a field tag PubMed ignored, a phrase it matched nothing for, a dateRange dropped for having one bound, no matches at all, or paging past the end. Absent when nothing applies."
    • changedOutput schema / properties / summaries / items / properties / doi / description
      Previous value: -"DOI"New value: +"DOI, cased as NCBI reports it. DOIs are case-insensitive by spec and no case normalization is applied here, so casing can differ from a Europe PMC-sourced `doi` — compare the two case-insensitively."
  6. Changed3 schema fields changedv2.9.4
    • addedOutput schema / properties / totalCount
      Added value: +{
      +  "description": "Total matching articles",
      +  "type": "number"
      +}
    • removedOutput schema / properties / totalFound
      Removed value: -{
      -  "description": "Total matching articles",
      -  "type": "number"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "query",
      -  "offset",
      -  "pmids",
      -  "summaries",
      -  "searchUrl",
      -  "effectiveQuery",
      -  "totalFound",
      -  "appliedFilters"
      -]New value: +[
      +  "query",
      +  "offset",
      +  "pmids",
      +  "summaries",
      +  "searchUrl",
      +  "effectiveQuery",
      +  "totalCount",
      +  "appliedFilters"
      +]
  7. Changed1 schema field changedv2.7.8
    • changedOutput schema / required
      Previous value: -[
      -  "query",
      -  "effectiveQuery",
      -  "appliedFilters",
      -  "totalFound",
      -  "offset",
      -  "pmids",
      -  "summaries",
      -  "searchUrl"
      -]New value: +[
      +  "query",
      +  "offset",
      +  "pmids",
      +  "summaries",
      +  "searchUrl",
      +  "effectiveQuery",
      +  "totalFound",
      +  "appliedFilters"
      +]
  8. Addedv2.7.6
  9. Removedv2.7.4
  10. Changed30 schema fields changedv2.3.2
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / author
      Added value: +{
      +  "description": "Filter by author name (e.g. \"Smith J\")",
      +  "type": "string"
      +}
    • removedInput schema / properties / dateRange / additionalProperties
      Removed value: -false
    • changedInput schema / properties / dateRange / description
      Previous value: -"Defines an optional date range for the search."New value: +"Filter by date range"
    • changedInput schema / properties / dateRange / properties / dateType / description
      Previous value: -"The type of date to filter by: 'pdat' (Publication Date), 'mdat' (Modification Date), 'edat' (Entrez Date). Default is 'pdat'."New value: +"Date type: pdat (publication), mdat (modification), edat (entrez)"
    • changedInput schema / properties / dateRange / properties / maxDate / description
      Previous value: -"The end date for the search range (YYYY, YYYY/MM, or YYYY/MM/DD)."New value: +"End date (YYYY/MM/DD, YYYY/MM, or YYYY)"
    • removedInput schema / properties / dateRange / properties / maxDate / pattern
      Removed value: -"^\\d{4}(\\/\\d{2}(\\/\\d{2})?)?$"
    • changedInput schema / properties / dateRange / properties / minDate / description
      Previous value: -"The start date for the search range (YYYY, YYYY/MM, or YYYY/MM/DD)."New value: +"Start date (YYYY/MM/DD, YYYY/MM, or YYYY)"
    • removedInput schema / properties / dateRange / properties / minDate / pattern
      Removed value: -"^\\d{4}(\\/\\d{2}(\\/\\d{2})?)?$"
    • addedInput schema / properties / dateRange / required
      Added value: +[
      +  "minDate",
      +  "maxDate"
      +]
    • removedInput schema / properties / fetchBriefSummaries
      Removed value: -{
      -  "default": 0,
      -  "description": "Number of top PMIDs for which to fetch brief summaries using ESummary. Set to 0 to disable. Max 50. Default 0.",
      -  "maximum": 50,
      -  "minimum": 0,
      -  "type": "integer"
      -}
    • removedInput schema / properties / filterByPublicationTypes
      Removed value: -{
      -  "description": "An array of publication types to filter by (e.g., [\"Review\", \"Clinical Trial\"]).",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • addedInput schema / properties / freeFullText
      Added value: +{
      +  "description": "Only include free full text articles",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / hasAbstract
      Added value: +{
      +  "description": "Only include articles with abstracts",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / journal
      Added value: +{
      +  "description": "Filter by journal name",
      +  "type": "string"
      +}
    • addedInput schema / properties / language
      Added value: +{
      +  "description": "Filter by language (e.g. \"english\")",
      +  "type": "string"
      +}
    • changedInput schema / properties / maxResults / description
      Previous value: -"Maximum number of articles to retrieve. Corresponds to ESearch's 'retmax' parameter. Default is 20, max is 1000."New value: +"Maximum results to return"
    • removedInput schema / properties / maxResults / exclusiveMinimum
      Removed value: -0
    • addedInput schema / properties / maxResults / minimum
      Added value: +1
    • addedInput schema / properties / meshTerms
      Added value: +{
      +  "description": "Filter by MeSH terms",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Result offset for pagination (0-based)",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedInput schema / properties / publicationTypes
      Added value: +{
      +  "description": "Filter by publication type (e.g. \"Review\", \"Clinical Trial\", \"Meta-Analysis\")",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / query
      Added value: +{
      +  "description": "PubMed search query (supports full NCBI syntax)",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • removedInput schema / properties / queryTerm
      Removed value: -{
      -  "description": "The primary keyword or phrase to search for in PubMed. Must be at least 3 characters long.",
      -  "minLength": 3,
      -  "type": "string"
      -}
    • addedInput schema / properties / sort
      Added value: +{
      +  "default": "relevance",
      +  "description": "Sort order: relevance (default), pub_date (newest first), author, or journal",
      +  "enum": [
      +    "relevance",
      +    "pub_date",
      +    "author",
      +    "journal"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / sortBy
      Removed value: -{
      -  "default": "relevance",
      -  "description": "Sorting criteria for results. Options: 'relevance' (default), 'pub_date', 'author', 'journal_name'.",
      -  "enum": [
      -    "relevance",
      -    "pub_date",
      -    "author",
      -    "journal_name"
      -  ],
      -  "type": "string"
      -}
    • addedInput schema / properties / species
      Added value: +{
      +  "description": "Filter by species",
      +  "enum": [
      +    "humans",
      +    "animals"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / summaryCount
      Added value: +{
      +  "default": 0,
      +  "description": "Fetch brief summaries for top N results (0 = PMIDs only)",
      +  "maximum": 50,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "queryTerm"
      -]New value: +[
      +  "query"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "offset": {
      +      "description": "Result offset used",
      +      "type": "number"
      +    },
      +    "pmids": {
      +      "description": "PubMed IDs",
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "query": {
      +      "description": "Original query",
      +      "type": "string"
      +    },
      +    "searchUrl": {
      +      "description": "PubMed search URL",
      +      "type": "string"
      +    },
      +    "summaries": {
      +      "description": "Brief summaries (empty array when summaryCount is 0)",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "authors": {
      +            "description": "Formatted author string",
      +            "type": "string"
      +          },
      +          "doi": {
      +            "description": "DOI",
      +            "type": "string"
      +          },
      +          "pmcId": {
      +            "description": "PMC ID",
      +            "type": "string"
      +          },
      +          "pmcUrl": {
      +            "description": "PMC URL",
      +            "type": "string"
      +          },
      +          "pmid": {
      +            "description": "PubMed ID",
      +            "type": "string"
      +          },
      +          "pubDate": {
      +            "description": "Publication date",
      +            "type": "string"
      +          },
      +          "pubmedUrl": {
      +            "description": "PubMed URL",
      +            "type": "string"
      +          },
      +          "source": {
      +            "description": "Journal source",
      +            "type": "string"
      +          },
      +          "title": {
      +            "description": "Article title",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "pmid"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "totalFound": {
      +      "description": "Total matching articles",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "query",
      +    "totalFound",
      +    "offset",
      +    "pmids",
      +    "summaries",
      +    "searchUrl"
      +  ],
      +  "type": "object"
      +}
  11. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the return shape (PMIDs with optional brief summaries) and the existence of offset paging, but omits the hard 9999-record ceiling and the rejection rules for malformed queries, both of which live 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.

Conciseness4/5

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

Three sentences, front-loaded with the verb and resource, then scope, then paging behavior. No filler, though the filter enumeration in the second sentence is largely redundant with the schema the agent will already read.

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

Completeness3/5

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

An output schema exists so return values needn't be re-explained, and annotations cover safety. Still, for a 14-parameter search tool with an overlapping sibling search tool, the description never addresses which search tool to pick or the result-set ceiling, leaving that routing and limit information to be discovered elsewhere.

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%, so the schema already documents all 14 parameters, including enums, defaults, bounds, and rejection rules for blank/whitespace values. The description merely restates categories of filters (author, journal, MeSH, language, species, free full text) without adding syntax or semantics beyond the schema, which is the expected baseline.

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 ('Search PubMed') and enumerates the capability surface: full query syntax, filters, date ranges, and return of PMIDs/summaries. It does not, however, distinguish itself from the sibling pubmed_europepmc_search, which is also a literature search tool, so an agent gets no in-description routing signal.

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

Usage Guidelines3/5

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

Usage is only implied: the mention of offset for 'paging through large result sets' hints at large-retrieval scenarios, and the summaryCount semantics (carried in the schema, not the description) imply handing leftover PMIDs to pubmed_fetch_articles. There is no explicit when-to-use-this-vs-europepmc_search guidance or any stated exclusion.

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