Skip to main content
Glama

start_document_upload

Destructive

Escribe un documento SUBIENDO UN ARCHIVO, sin que el contenido pase por el modelo. Es la forma rápida para contenido largo (más de ~20 KB) o que ya está en un archivo.

Devuelve `upload_url`. Subí el archivo (markdown o HTML) con UN comando y listo — el PUT escribe el documento:
  curl -X PUT "<upload_url>" --data-binary @documento.md
La respuesta del curl trae el `resumen` (bytes, bloques, tablas, títulos, sha256): no hace falta llamar a nada más.

Con document_id: REEMPLAZA el contenido de ese documento (base_version opcional, igual que update_document).
Con name (sin document_id): crea un documento nuevo, ya, y la subida le pone el contenido.
El permiso vence en 2 horas y sirve para ese documento solo.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_document_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoNombre de un documento NUEVO (sin document_id)
document_idNoDocumento a reemplazar
base_versionNoCon document_id: updated_at con el que se leyó
workspace_idNoUUID del workspace, o su nombre tal como lo dice el usuario ('Acme', 'el personal'). Omitir si el token ya tiene workspace fijo
parent_document_idNoCon name: documento padre del nuevo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the return value (upload_url), the exact follow-up step (a single PUT via curl), and that the PUT response already contains the summary (bytes, blocks, tables, titles, sha256) so no further call is needed. It also warns that the permission expires in 2 hours and is scoped to a single document, and that passing document_id replaces existing content — consistent with destructiveHint=true.

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 purpose and the size criterion, then structured into a concrete command and per-mode rules; the emphasis and code block make it scannable. It is longer than most definitions but nearly every sentence carries operational information, with only minor casual 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?

For a two-step upload tool with no output schema, the description covers what is returned, how to complete the upload, what the follow-up response contains, permission lifetime and scope, and both modes of operation. Nothing an agent needs to invoke it correctly 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 100%, so the baseline is 3, but the description adds real meaning: name creates a new document, document_id switches to replacement, and base_version is optional and behaves like update_document. workspace_id and parent_document_id are left entirely to the schema.

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 and resource ("Escribe un documento SUBIENDO UN ARCHIVO") and immediately disambiguates scope: content never passes through the model, and this is the fast path for large or already-filed content. The contrast with the direct-content path (short content written by the model) is implicit but clear enough that an agent can pick between this and create_document/update_document.

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 an explicit threshold (~20 KB) and a condition (content already in a file) for when to choose this tool, plus a clear branch between the replace mode (with document_id) and the create mode (with name only). It does not name the sibling it should be used instead of for short content, so the exclusion is inferred rather than stated.

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