Campus Virtual MCP

get_course_resources

Read-onlyIdempotent

Lists accessible links and materials for a course, including assignments, PDFs, ZIPs, pages, and URLs, with section, module, and source details so users can locate course resources.

Instructions

Lista los enlaces de una asignatura, incluidas tareas y archivos PDF, ZIP y otros.

Recorre secciones topics/onetopic accesibles; lee carpetas, recursos, enlaces URL, páginas y adjuntos de consignas de tareas. Devuelve links con sección, módulo y source_url. Los enlaces de tareas abren la actividad de entrega; no envía archivos. Autentica con .env. No visita sitios externos ni descarga binarios. Solo contenido visible para la cuenta: no inventa enlaces de actividades o secciones restringidas. Revisá complete, pending_urls y warnings antes de asumir que el inventario es completo. No recorre conversaciones de foros, intentos de exámenes ni sitios externos.

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": {
      "course_id": "<course_id>"
    },
    "name": "get_course_resources"
  }
}

Input Schema

Name	Required	Description	Default
`course_id`	Yes	ID de la asignatura de Grado.

Output Schema

Name	Required	Description	Default
`links`	Yes
`total`	Yes
`course`	Yes
`format`	Yes
`complete`	Yes
`sections`	Yes
`warnings`	Yes
`fetched_at`	Yes
`pending_urls`	Yes
`unlinked_activities`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial context beyond the annotations: authentication via .env, the returned link fields (section, module, source_url), the fact that assignment links point at the submission activity rather than uploading, permission scoping to what the account can see, and a directive to inspect complete/pending_urls/warnings before trusting completeness. The openWorldHint=true annotation is consistent with pulling data from an external LMS, and the 'no external sites' clause scopes traversal rather than contradicting it.

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?

Purpose is front-loaded in sentence one and the remaining lines are structured as constraints, returns, and caveats rather than prose. Minor waste from repetition: the 'no external sites' restriction appears in two separate places, and the forum/exam exclusions could be folded into one clause.

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 single-parameter read tool with annotations and an output schema, everything an agent needs is present: what is traversed, what is deliberately skipped, what the return keys mean, and the completion flags to check. Nothing material is left to inference.

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?

Only one parameter exists and its schema description ("ID de la asignatura de Grado") is complete, so the schema carries the load. The description adds only implicit guidance — that the tool operates on a single course's sections — without explaining any format or sourcing of the ID, which keeps it just above the 100%-coverage baseline of 3.

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 sentence states a specific verb and resource ("Lista los enlaces de una asignatura") and immediately scopes the content types covered (tareas, PDF, ZIP, otros). It also distinguishes the tool from download_resources by declaring that it returns links and does not download binaries, so an agent can separate the two without inspecting either schema.

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?

Offers clear contexts for use (build a link inventory of accessible topics/onetopic sections) plus explicit exclusions: no forums, no exam attempts, no external sites, no binary downloads. The gap is that it never names the alternative sibling tools (download_resources, list_courses) nor states that course_id must come from list_courses.

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

Deploy Server