Skip to main content
Glama

Search Canvas

canvas_search
Read-onlyIdempotent

Search across all Canvas classes for syllabus pages, announcements, course pages, and assignment titles or instructions to find answers and links.

Instructions

Search all of the user's Canvas classes at once: syllabus pages, announcements (about a semester back), course pages, and assignment titles and instructions. Use it for questions like "is the exam open-book?", "what's on Exam 2?", "where's the lab handout?". Returns the best matches with class, type, date and link; follow up with canvas_assignment / canvas_page / canvas_announcements for the full text. Read-only.

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": {
      "query": "<query>"
    },
    "name": "canvas_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real behavior: the announcement lookback window ("about a semester back") and the fact that results are ranked best-matches with metadata rather than full text, requiring a follow-up call. The trailing "Read-only" is redundant with the annotations but harmless.

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?

Front-loaded with scope, then example queries, then return shape and follow-up routing — a logical order with no filler. The example questions are load-bearing for parameter semantics, though the closing "Read-only." duplicates the annotations and could be cut.

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 one-parameter search tool with an output schema, this covers everything an agent needs: what corpora are searched, the temporal window, what comes back (class, type, date, link), and which tools to chain into for full text. No open question remains before invoking it.

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 0% for the single `query` parameter, so the description must carry the meaning — and it does, by framing the input as a natural-language question via three example phrasings, implying semantic search rather than keyword syntax. It does not specify matching behavior (fuzzy vs exact) or result limits, so it stops short of a 5.

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 ("Search all of the user's Canvas classes") and enumerates exactly what is searched: syllabus pages, announcements, course pages, and assignment titles/instructions. This clearly distinguishes it from the sibling retrieval tools (canvas_page, canvas_assignment, canvas_announcements) which fetch full documents rather than matching.

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?

Gives concrete example questions ("is the exam open-book?", "where's the lab handout?") that define the intended query class, and explicitly routes the agent onward to canvas_assignment / canvas_page / canvas_announcements once a match is found. The when-to-use and what-to-do-next are both spelled out.

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