Skip to main content
Glama

Find a person in the BnF authority file

search_authors
Read-onlyIdempotent

Finds a person in the BnF authority file by exact name and returns the identifier other tools require, using birth year, death year, and role to separate same-name records.

Instructions

Find a person in the Bibliothèque nationale de France authority file by name, and get the identifier the other tools take. This matches the name the BnF records, so it takes a surname, a full name or both names in either order. It does not read biographies, so it cannot find a person from what they wrote or what they did. It reads the person records and nothing else: an organisation, a conference or a place is outside it, and an answer holding no row says nothing about those. The match is letter for letter, so a name written with other accents or under another transliteration is a different search: try the spellings a library would use before concluding the BnF holds nobody of that name. Several rows can carry one name: the BnF keeps more than one authority record for some people, and many people share a name. Read 'birth_year', 'death_year' and 'role' to tell them apart, and show the caller the choice rather than picking one. Rows come back ordered by the address of the record, which is not an order of relevance. That order is the one the pages are cut along, so paging through a search reaches every match once. One search reads a fixed window of the index. 'index_window_full' says whether that window came back full: when it did, names sit past what was read, 'has_more' being false says where the reading stopped, and another reading of the same search can bring back other rows. Narrow the name to reach further.

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": {
      "name": "<name>"
    },
    "name": "search_authors"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe person's name, such as 'Rimbaud' or 'Arthur Rimbaud'.
pageNo
limitNo

Output Schema

NameRequiredDescriptionDefault
nameYesThe name asked for.
pageYes
notesYes
authorsYes
has_moreYesWhether the endpoint held at least one further row beyond this page, within the window the search read off the index. Read it alongside 'index_window_full': false on a full window says where the reading stopped rather than that the file holds nobody else.
retrieved_atYesWhen these metadata were read from data.bnf.fr, as an ISO 8601 instant. The BnF licence asks for this date to be stated wherever the metadata are shown, so repeat it alongside the source.
words_searchedYesThe terms the index required, each of which has to appear in the name. A word is cut at an apostrophe and at a hyphen before the index sees it, so a name written as one word can appear here as two, and a record carrying the pieces apart is a match.
index_window_fullYesWhether the fixed window this search reads off the index came back full. True means records carrying these words sit past what was read, so the rows here are a part of the matches and another reading can bring back other rows. False means the window held everything that matched. Null when the endpoint stated no occupancy, which claims nothing either way.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv2.2.0
    • removedOutput schema / properties / authors / items / properties / label / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / authors / items / properties / label / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / authors / items / properties / name / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / authors / items / properties / name / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / authors / items / properties / role / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / authors / items / properties / role / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / index_window_full / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / index_window_full / type
      Added value: +[
      +  "boolean",
      +  "null"
      +]
  2. Changed4 schema fields changedv1.1.0
    • changedOutput schema / properties / has_more / description
      Previous value: -"Whether the index held at least one further match beyond this page."New value: +"Whether the endpoint held at least one further row beyond this page, within the window the search read off the index. Read it alongside 'index_window_full': false on a full window says where the reading stopped rather than that the file holds nobody else."
    • addedOutput schema / properties / index_window_full
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Whether the fixed window this search reads off the index came back full. True means records carrying these words sit past what was read, so the rows here are a part of the matches and another reading can bring back other rows. False means the window held everything that matched. Null when the endpoint stated no occupancy, which claims nothing either way."
      +}
    • changedOutput schema / properties / words_searched / description
      Previous value: -"The words the index was actually asked for, after punctuation was set aside."New value: +"The terms the index required, each of which has to appear in the name. A word is cut at an apostrophe and at a hyphen before the index sees it, so a name written as one word can appear here as two, and a record carrying the pieces apart is a match."
    • changedOutput schema / required
      Previous value: -[
      -  "name",
      -  "words_searched",
      -  "authors",
      -  "page",
      -  "has_more",
      -  "retrieved_at",
      -  "notes"
      -]New value: +[
      +  "name",
      +  "words_searched",
      +  "authors",
      +  "page",
      +  "has_more",
      +  "index_window_full",
      +  "retrieved_at",
      +  "notes"
      +]
  3. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing matching semantics (letter-for-letter, accent and transliteration sensitive), duplicate-record behaviour, non-relevance ordering, page-cut ordering, and a bounded index window with 'index_window_full' and 'has_more' caveats. The one weak spot is that the window/has_more sentence is genuinely hard to parse and its practical implication ('another reading of the same search can bring back other rows') may confuse rather than clarify.

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 is front-loaded and most sentences carry unique information, but it is one dense paragraph mixing matching rules, entity scope, disambiguation, pagination and window semantics. Several sentences are convoluted ('an answer holding no row says nothing about those') and the has_more explanation is re-read twice, which costs clarity.

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?

With an output schema present, the description need not enumerate return fields, and it still highlights the disambiguating fields (birth_year, death_year, role) and the pagination signals. For a read-only search tool with a hard-capped index window, nothing an agent needs in order to call it and interpret results is missing.

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 only 33% (page and limit are undocumented), so the description must compensate. It adds real meaning for 'name' (surname, full name, or both in either order; accent-sensitive) and explains paging behaviour and the fixed index window, though it never ties limit explicitly to the 1–50 bound or says how page and limit interact.

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?

States the specific verb, resource and scope ('Find a person in the BnF authority file by name') and names the payoff ('get the identifier the other tools take'), which implicitly separates it from get_author. It also declares what the tool does not cover (biographies, organisations, conferences, places), so an agent can tell it apart from siblings without opening a schema.

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?

Gives explicit when-to-use context (name-based lookup feeding the identifier other tools take) and explicit exclusions: it cannot find a person from what they wrote or did, and an empty answer says nothing about non-person entities. It adds a concrete recovery tactic for null results (try the spellings a library would use) rather than leaving the agent to fail silently.

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