Skip to main content
Glama

canvas_pages

Read-onlyIdempotent

Lists a course or group's visible wiki pages with URLs, titles, and update times; when the page list is hidden, use modules or file search instead.

Instructions

List the wiki pages of a course or group that you can see, with their page_url, title and update time. Many courses hide this list (401/403/404); then find pages through canvas_modules or canvas_find_files.

Input Schema

NameRequiredDescriptionDefault
rawNotrue: Canvas's unmodified JSON (UTC times, HTML).
pageNoPage to fetch: a number, or the next_page value returned by the previous call.
context_idYesId of the course, group, user or folder named by context_type.
context_typeYesWhere to look: course or group (files and folders also take user or folder).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the remaining burden is small, and the description adds real value: results are permission-filtered ('that you can see') and many courses will return 401/403/404 rather than an empty list. It does not describe the response envelope or pagination semantics, but the hidden-list warning is the behavior an agent most needs.

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, zero filler: the first defines the action and payload, the second handles the failure case, in that priority order. Every clause earns its place.

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 correctly names the returned fields (page_url, title, update time) and covers the main operational hazard of a permission-gated listing. Minor gap: it does not state whether results are paginated or how large a page is, though the 'page' bookmark parameter hints at it.

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%, including the 'raw' and 'page' bookmark explanations, so the schema already carries parameter meaning. The description only implicitly conveys context_type ('course or group') and adds no syntax or format detail beyond that. Baseline 3 applies when the schema does the heavy lifting.

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 the wiki pages of a course or group') plus the visibility scope ('that you can see') and the three fields returned. An agent can distinguish this listing tool from the singular canvas_page / canvas_front_page siblings without opening any 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?

Gives an explicit fallback path for the common failure mode: if the list is hidden (401/403/404), use canvas_modules or canvas_find_files. It stops short of saying when to prefer this over canvas_page, canvas_context_page, or canvas_front_page, but the alternative routing for the blocked case is unusually concrete.

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