Search course content

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

Annotations already establish read-only and closed-world, and the description adds substantial behavior beyond them: searches work with no Canvas calls (local snapshot), matching is prefix-based, all words must appear, quoted phrases work, and there is an OR fallback when no document matches every term. It also discloses that results span linked file text (PDF pages, slides, document sections) and points to the follow-up tool.

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

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

Front-loaded with the verb and scope, then the matching rules, then the handoff to canvas_read_file. Dense but nearly every clause carries information (the file-text coverage and the OR fallback are both decision-relevant). Slightly crammed into two long sentences with nested parentheses, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does some work describing result semantics (file hits carry a page/slide for canvas_read_file) and explains the matching/ranking fallback so an agent can interpret empty-ish results. Remaining gap is the result shape for non-file kinds and the meaning of course_id, which for a 4-parameter search tool would be worth one more clause.

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

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

Schema coverage is 50%, and the description compensates well for query — explaining prefix matching, multi-word AND semantics, the example "dyn prog" → "dynamic programming", and quoted phrases — which the bare schema does not. It does not explain course_id at all (whether omitting it searches across all snapshot courses), leaving one undocumented parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — full-text search across snapshot courses — and enumerates the content types covered (pages, assignments, announcements, discussions, quizzes, events, modules, syllabus, file names, linked file text). This clearly separates it from the granular canvas_list_* / canvas_get_* siblings, which retrieve specific known items rather than searching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description establishes context (search the local snapshot, not live Canvas) and explicitly routes file hits onward: "File hits give the page/slide to pass to canvas_read_file." That is real alternative-naming. It stops short of an explicit 'use this when you don't know which course item holds the term, otherwise use canvas_list_pages/get_page' statement, so it is clear context rather than full when/when-not guidance.

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