Skip to main content
Glama

get_artifact

Read-onlyIdempotent

Trae un artefacto: su metadata y su historial de versiones. El contenido se pide de dos maneras y conviene elegir bien:

  · **buscar="…"** — devuelve SÓLO los pedazos del archivo donde aparece ese texto, con su contexto alrededor. Es la forma de leer para editar: ~800 caracteres en vez de los 107.000 del archivo, y lo que devuelve se pega tal cual en el `buscar` de patch_artifact. Dice además cuántas veces aparece, que es lo que hay que saber antes de parchear.
  · **incluir_contenido=true** — el HTML entero. Caro: un artefacto de 100 KB son ~50.000 tokens de entrada. Usarlo sólo si de verdad hace falta leerlo todo.

Cuando devuelve contenido, devuelve también `bytes` y `sha256` de esa versión, que sirven para verificar un guardado sin volver a bajar nada.

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": {
      "artifact_id": "<artifact_id>"
    },
    "name": "get_artifact"
  }
}

Input Schema

NameRequiredDescriptionDefault
buscarNoDevolver sólo los fragmentos donde aparece este texto (literal, no es una regex). Es la lectura barata.
versionNoQué versión leer (default: la actual)
contextoNoCuántos caracteres se devuelven a CADA lado de la coincidencia (default: 300)
artifact_idYesID del artefacto
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
incluir_contenidoNoTraer el HTML entero (caro). Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
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), so the description's job is added context — and it delivers: token/size cost of full-content reads, the fact that buscar returns match counts needed before patching, context characters around each hit, and that bytes/sha256 are returned to verify a save without re-downloading. These are non-obvious operational traits not derivable from annotations or 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?

The purpose is front-loaded in one sentence, then the two modes are laid out as scannable bullets with the cheap option first. The cost figures earn their space, though the definition runs long and repeats the expense warning for incluir_contenido in slightly different words.

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

Completeness4/5

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

For a read-only tool with no output schema and six parameters, the description covers the decisions that matter: which mode, why, and what comes back (bytes/sha256). It does not describe the shape of the metadata or version-history payload, which is the remaining gap given there is no output schema to fall back on.

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 each parameter is already documented, but the description adds consequence-level meaning the schema lacks: buscar is the cheap read-and-edit path whose output pastes directly into patch_artifact, and incluir_contenido is the expensive fallback. The version and contexto parameters are left to their schema descriptions, which is acceptable at full coverage.

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?

The opening line states a concrete verb and resource — fetching an artifact with its metadata and version history — and then explicitly splits content retrieval into two named modes (buscar vs incluir_contenido). It also differentiates itself practically by naming patch_artifact as the consumer of buscar output, so an agent can place it among siblings without opening the 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?

It gives explicit when-to-use guidance for each mode with the decision rule spelled out: buscar is 'la forma de leer para editar' at ~800 characters, while incluir_contenido should only be used 'si de verdad hace falta leerlo todo'. The cost asymmetry (~800 chars vs 107,000; ~50,000 tokens for 100 KB) makes the tradeoff actionable rather than implied.

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