Skip to main content
Glama
Moodle MCP (Aula USM)

Moodle MCP (Aula USM)

by muitomou

descargar_material

Idempotent

Download course materials into a linked local course folder, filtered by resource ID or search text, or retrieve the whole course; existing files are kept unless overwrite is enabled.

Instructions

Descarga archivos de un ramo a su carpeta local, en /Aula/<sección>/.

Filtra por recurso_id (de contenido_ramo) o por texto en buscar; todo=true baja todo el ramo. No sobrescribe archivos existentes salvo con sobrescribir=true. Si el ramo no tiene carpeta vinculada y no hay una única coincidencia, responde con candidatos para usar vincular_carpeta.

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": {
      "ramo": "<ramo>"
    },
    "name": "descargar_material"
  }
}

Input Schema

NameRequiredDescriptionDefault
ramoYes
todoNo
buscarNo
recurso_idNo
sobrescribirNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare a non-read, non-destructive, idempotent, open-world write; the description adds genuinely new behavior: files land in <carpeta del ramo>/Aula/<sección>/, existing files are preserved unless sobrescribir=true, and an unresolved course folder returns candidate names rather than failing silently. It does not cover partial-download failures or permission/auth requirements, which matters for a filesystem writer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences: destination and action first, filtering modes second, side effects and failure mode last. No filler and nothing repeated from the schema or annotations.

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?

An output schema exists, so return values need no explanation, and the description still flags the candidate-list response on folder failure. Remaining gap is edge-case behavior: how todo interacts with recurso_id/buscar, and whether a partial write leaves files behind.

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?

With 0% schema description coverage the description must carry the parameters, and it explains recurso_id's origin in contenido_ramo, `buscar` as text matching, todo=true as the bulk mode, and sobrescribir's overwrite semantics. Only `ramo` itself is left implicit (assumed from the destination path), and the precedence when todo and a filter are combined is unstated.

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?

Opens with a specific verb and resource ("Descarga archivos de un ramo") plus the exact destination path template, which no sibling would produce. The mention of contenido_ramo as the source of recurso_id and vincular_carpeta as the fallback implicitly separates it from the listing/reading tools.

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 three concrete selection modes (recurso_id, `buscar` text, todo=true) and an explicit fallback: when no folder is linked and there is no unique match, use vincular_carpeta. It stops short of stating when not to use it (e.g. reading content in place with leer_material instead of downloading).

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