Skip to main content
Glama
Fireiscoolsolo

Canvas LMS MCP – Remote Edition

by Fireiscoolsolo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

List Course Files

list_course_files
Read-onlyIdempotent

Retrieves a Canvas course’s files—slides, readings, and handouts—with names, sizes, types, and IDs, and supports filtering by name or content type. Read-only.

Instructions

List files in a course (slides, readings, handouts) with names, sizes, types and IDs, optionally filtered by name or type. Read-only. Save one with download_file, or all with download_all_course_files.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of items to return. Smaller is faster.
course_idYesCanvas course ID, a numeric string such as "12345". Get it from list_courses.
search_termNoOptional text filter on names or titles (at least 2 characters, case-insensitive).
content_typesNoe.g. application/pdf

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.1.3
    • changedInput schema / properties / course_id / description
      Previous value: -"Canvas course ID"New value: +"Canvas course ID, a numeric string such as \"12345\". Get it from list_courses."
    • changedInput schema / properties / limit / description
      Previous value: -"Max items to return"New value: +"Maximum number of items to return. Smaller is faster."
    • addedInput schema / properties / search_term / description
      Added value: +"Optional text filter on names or titles (at least 2 characters, case-insensitive)."
  2. First observedv0.1.0

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so 'Read-only' in the description merely restates structured data. The mention of returned fields (names, sizes, types, IDs) adds real context absent from annotations, but there is no word on pagination or how 'limit' truncates results, which matters for an open-world list endpoint.

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?

Two sentences, no filler: the first covers scope, contents and return fields; the second covers the safety profile and the follow-up tools. Everything the agent needs comes before the optional detail.

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?

With no output schema, the description usefully enumerates the returned attributes and names the natural follow-on download tools, which is enough for correct invocation. The gap is pagination/limit behavior on a potentially large listing, though the schema's own 'smaller is faster' note partly compensates.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented, and the description only echoes the filtering behavior of search_term/content_types. It adds nothing about the 'limit' tradeoff ('smaller is faster') or the MIME-format expectation for content_types beyond what the schema states.

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 ('List files in a course') and immediately qualifies the scope with examples of the content (slides, readings, handouts) and the returned fields. The 'in a course' framing plus the required course_id separates it from list_my_files and list_group_files without the agent needing to open a 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?

Explains the optional filtering ('optionally filtered by name or type') and routes the agent forward to download_file for one file or download_all_course_files for everything. It stops short of stating when NOT to use it or naming list_my_files/list_group_files as the alternative scopes, so it isn't a full when/when-not treatment.

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

Deploy Server

Other Tools