audit_course_accessibility

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

Annotations indicate readOnlyHint=true and openWorldHint=true. The description extensively adds behavioral context: it is a read-only scan, describes output format (WCAG criterion, severity), limitations (no color contrast, no list-misuse), opt-in quiz scanning, and permission requirements. No contradiction with annotations exists.

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?

The description is comprehensive but dense; every sentence contributes essential information (purpose, checks, limitations, opt-in, comparison). It is well-structured with a logical flow, though slightly lengthy. No unnecessary words or repetition.

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?

Given no output schema, the description adequately explains the return format (WCAG criterion and severity) and distinguishes error vs. advisory findings. It covers all key aspects: what is scanned, what is not, permissions, and integration with other tools. The tool has only 2 parameters, and the description fully addresses its behavior.

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 100% with both parameters described. The description adds value by explaining the default content sources for the 'include' parameter and explicitly stating quizzes as opt-in. This clarifies usage beyond the schema's basic descriptions.

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?

The description clearly states the tool scans course content for structurally-detectable WCAG 2.1 accessibility problems, listing specific checks (images, links, headings, tables) and limitations. It distinguishes itself from sibling tools by focusing on accessibility auditing, whereas siblings like 'audit_course_links' handle link verification. The purpose is specific and unambiguous.

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 explains when to use the tool (for structural accessibility scanning) and what it does not cover (color contrast, list misuse). It notes it complements Canvas's Accessibility Checker. However, it does not explicitly name alternative sibling tools or provide when-not-to-use scenarios, leaving some room for improvement.

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