Skip to main content
Glama

get_document

Read-onlyIdempotent

Lee un documento. Por defecto devuelve el contenido como MARKDOWN (format), una sola vez y sin duplicar.

format: "markdown" (default) — títulos, listas, tablas, enlaces; es lo que aceptan create/update/patch/append.
        "texto" — texto plano, sin marcas.
        "crudo" — lo guardado tal cual (HTML o el JSON de bloques del editor). Rara vez hace falta.
buscar: en vez del documento entero, sólo los fragmentos (del markdown) donde aparece ese texto, con contexto.
        Es lo que hay que usar en un documento largo para saber QUÉ cambiar con patch_document.

Devuelve también `updated_at`: pasalo como `base_version` al escribir y la escritura falla si alguien
cambió el documento en el medio, en vez de pisarlo. `perdidas` lista lo que el markdown no representa
(fórmulas, referencias a otros documentos, colores…): si no está vacío, patch_document y append_document
no se pueden usar sobre ese documento.

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": {
      "document_id": "<document_id>"
    },
    "name": "get_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
buscarNoDevolver sólo los fragmentos que contienen este texto
formatNoFormato del contenido (default: markdown)
contextoNoCon buscar: caracteres de contexto a cada lado (default 300)
document_idYesID del documento
workspace_idNoUUID del workspace, o su nombre tal como lo dice el usuario ('Acme', 'el personal'). Omitir = TODOS los workspaces de la persona, en una sola llamada

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real behavior: content is returned once without duplication, `updated_at` is returned and can be passed as `base_version` so a write fails rather than clobbering a concurrent edit, and `perdidas` enumerates what markdown does not represent (formulas, cross-references, colors). That is exactly the kind of concurrency and fidelity information annotations cannot express.

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-loaded with the core action and the default, then block-structured per parameter, so an agent can skim. The format block is slightly verbose in enumerating markdown elements, but nearly every clause carries operational information; nothing is pure filler.

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 no output schema, the description compensates by naming the meaningful return fields (`updated_at`, `perdidas`) and their downstream consequences. For a five-parameter read tool, an agent has everything needed to call it correctly and to interpret the result before writing.

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 the baseline is 3, but the description goes further by explaining what each `format` value actually yields (headings/lists/tables/links vs plain text vs raw HTML or editor block JSON) and what `buscar` returns (markdown fragments with context). `contexto` and `workspace_id` are left to the schema, which already documents them adequately.

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?

"Lee un documento" states a specific verb and resource, and the description immediately narrows scope by declaring the default return shape (MARKDOWN, returned once, not duplicated). It distinguishes itself from write siblings by naming patch_document and append_document, though it never contrasts itself with list-style siblings like get_documents.

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 explicit when-to-use guidance: "buscar" is what to use on a long document "para saber QUÉ cambiar con patch_document", and "crudo" is flagged as "Rara vez hace falta". It also states a hard when-not: patch_document and append_document cannot be used when `perdidas` is non-empty. It stops short of routing between get_document and the listing/version siblings.

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.

Resources