Audit Course Accessibility

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

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses the severity taxonomy (error vs advisory), the dependency on rendered theme CSS for the excluded color-contrast check, the opt-in default for quizzes, and the permission requirement. No contradiction with annotations — 'Scan' confirms the readOnlyHint=true safety profile.

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?

Each of the six sentences earns its place: purpose, findings, severity, exclusions, opt-in behavior, alternative tool, permissions. It is front-loaded with verb and resource, but the single dense paragraph could be broken into scannable sections for faster agent parsing.

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?

Complete for a 2-param read-only tool: parameters are 100% schema-covered, annotations cover the safety profile, and because there is no output schema, the description compensates by stating that each finding carries a WCAG success criterion and severity. Permissions, limitations, and alternatives are all present.

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 description coverage is 100%, and the include parameter's schema text already documents the default four sources and the quizzes opt-in, so the schema carries the load. The description reinforces the quizzes opt-in but adds no parameter meaning beyond what the schema already provides.

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 precise verb ('scan'), a specific resource (course content: pages, assignments, syllabus, announcements, optionally quizzes), and enumerates the exact problem classes detected (missing/low-quality alt text, non-descriptive links, duplicate links, heading issues, table issues). The scope delimiter 'structurally-detectable' plus named exclusions cleanly separate it from sibling auditing tools such as audit_course_links.

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?

Explicitly frames when NOT to use it: 'Complements — does not replace — Canvas's own in-app Accessibility Checker,' which covers rendered color contrast and offers in-UI remediation. It also states the prerequisite ('Requires instructor permissions in the course') and the structural-only boundary, so an agent can route color-contrast requests elsewhere.

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