Skip to main content
Glama

Gather the digitised documents attached to a record

find_digitised
Read-onlyIdempotent

Retrieve links to digitised documents from the BnF catalogue for a person or work identifier, following editions or record images as appropriate.

Instructions

Gather the digitised documents the Bibliothèque nationale de France catalogue attaches to one person or one work, and return them as links. Give the identifier of either; the tool asks the catalogue what kind of record it is and follows the right path. For a work it walks the editions; for a person it takes the images on the record and the digitised editions of the works they are credited with. The 'kind' returned is what the catalogue types the record as. Every result is a link for someone to open. This server reads the BnF catalogue and never requests gallica.bnf.fr, so it reports nothing about what is at the other end: not whether the document opens, not what it contains, not on what terms it may be reused. It returns links and nothing else: no publisher, no date, no ISBN. Use list_editions when which edition a copy belongs to matters. A 'depiction' illustrates a record and can be a page that merely mentions the subject. A 'reproduction' is an edition digitised. An 'ocr' link names a machine-read text of a document, which this server does not fetch.

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": {
      "id": "<id>"
    },
    "name": "find_digitised"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesA person or work identifier, such as 'cb119219976' or 'cb11970626n'. The argument is named 'id' rather than 'work_id' or 'author_id' because it takes either.
kindNoWhat you expect the identifier to name. The catalogue is asked either way, and a kind it contradicts is refused rather than followed. 'auto' states no expectation.auto
limitNo

Output Schema

NameRequiredDescriptionDefault
idYes
kindYesWhat the catalogue types this record as.
linksYes
notesYes
has_moreYes
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.
links_returned_by_roleYesHow many of the links in this answer carry each role. These count the links returned here, which is neither a count of documents nor a count of what the catalogue attaches: several links can name one document, and 'has_more' says when links were left out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.2.0
    • removedOutput schema / properties / links / items / properties / from_title / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / links / items / properties / from_title / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / links / items / properties / rendering / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / links / items / properties / rendering / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  2. Changed7 schema fields changedv1.1.0
    • changedInput schema / properties / kind / description
      Previous value: -"Which kind of record the identifier names. 'auto' asks the catalogue, which costs one extra query."New value: +"What you expect the identifier to name. The catalogue is asked either way, and a kind it contradicts is refused rather than followed. 'auto' states no expectation."
    • removedOutput schema / properties / counts
      Removed value: -{
      -  "additionalProperties": false,
      -  "description": "Links returned on this page, by role. These count links, not documents.",
      -  "properties": {
      -    "depiction": {
      -      "maximum": 9007199254740991,
      -      "minimum": -9007199254740991,
      -      "type": "integer"
      -    },
      -    "ocr": {
      -      "maximum": 9007199254740991,
      -      "minimum": -9007199254740991,
      -      "type": "integer"
      -    },
      -    "reproduction": {
      -      "maximum": 9007199254740991,
      -      "minimum": -9007199254740991,
      -      "type": "integer"
      -    }
      -  },
      -  "required": [
      -    "reproduction",
      -    "ocr",
      -    "depiction"
      -  ],
      -  "type": "object"
      -}
    • addedOutput schema / properties / links / items / properties / rendering
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The view the address asks Gallica for, read off what follows the ARK name in it, such as 'thumbnail' for a small image or 'item' for one leaf. Null when the address names the document itself. This says what was asked for, not what comes back."
      +}
    • changedOutput schema / properties / links / items / properties / url / description
      Previous value: -"Open this to see the document. This server does not read it."New value: +"The address the catalogue publishes, for a person to open. Read it beside 'rendering': an address asking for a rendering opens that view of the document rather than the document. This server does not read either."
    • changedOutput schema / properties / links / items / required
      Previous value: -[
      -  "ark",
      -  "url",
      -  "role",
      -  "from_id",
      -  "from_title"
      -]New value: +[
      +  "ark",
      +  "url",
      +  "rendering",
      +  "role",
      +  "from_id",
      +  "from_title"
      +]
    • addedOutput schema / properties / links_returned_by_role
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "How many of the links in this answer carry each role. These count the links returned here, which is neither a count of documents nor a count of what the catalogue attaches: several links can name one document, and 'has_more' says when links were left out.",
      +  "properties": {
      +    "depiction": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "ocr": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "reproduction": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    }
      +  },
      +  "required": [
      +    "reproduction",
      +    "ocr",
      +    "depiction"
      +  ],
      +  "type": "object"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "id",
      -  "kind",
      -  "links",
      -  "counts",
      -  "has_more",
      -  "retrieved_at",
      -  "notes"
      -]New value: +[
      +  "id",
      +  "kind",
      +  "links",
      +  "links_returned_by_role",
      +  "has_more",
      +  "retrieved_at",
      +  "notes"
      +]
  3. First observedv1.0.0

TDQS

A4.8/5.0
Behavior5/5

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

Goes well past the annotations: it declares the server never requests gallica.bnf.fr, so nothing is known about whether links open, what they contain, or reuse terms. It also states output is links only (no publisher, date, ISBN) and that a contradictory 'kind' is refused rather than followed — none of which annotations convey.

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?

Front-loads what it does and what it returns, then the caveats, with no filler sentences. It is on the long side, and the trailing glossary of depiction/reproduction/ocr could be tightened, but each sentence carries information.

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?

Despite an output schema existing, the description usefully frames what the results mean (links only, 'kind' is the catalogue's typing) and sets expectations that the links are unverified. Nothing an agent needs to interpret the output or avoid misusing it 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?

Explains that 'id' accepts either a person or work identifier and that the tool resolves the record type itself, and clarifies the 'kind' guard behavior beyond the schema text. The 'limit' parameter is left undocumented, which schema coverage (67%) does not fully compensate for.

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 a specific verb ('gather the digitised documents') and resource ('the BnF catalogue attaches to one person or one work') with the return form ('return them as links'). It is clearly distinguishable from siblings like list_editions and get_work, which return bibliographic data rather than digitised links.

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 routes away from a sibling: 'Use list_editions when which edition a copy belongs to matters.' It also disambiguates the three result kinds (depiction, reproduction, ocr) so an agent knows what it will get and which to care about.

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