fix_accessibility_issues

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

Annotations declare destructiveHint: true and idempotentHint: true. The description explains the dry_run default (preview only, apply with flag set to false) which directly addresses the destructive nature and adds safety context. It doesn't contradict annotations; it complements them. The description also clarifies the flow (scan first, then fix). Slight gap: doesn't explicitly say 'this permanently modifies course content' but dry_run explanation implies it.

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?

Description opens with a clear verb+resource sentence, then a compact 2-line workflow. No fluff. The two-step instruction (scan first) is front-loaded. Slightly redundant with schema's dry_run description, but overall efficient.

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?

Covers the key operational context: what it fixes, the prerequisite scan step, and the safety default. Given the schema covers all params and the tool has no output schema (not needed for an action tool), this is complete enough. It doesn't mention return values, but they're minimal for a fix operation.

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?

The input schema covers all 4 parameters with 100% description coverage-held, so baseline is 3. The description reinforces dry_run semantics but doesn't add syntax or deeper meaning beyond the schema. The fix_types list is in the schema enumeration, so minimal added value.

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?

Description clearly states it auto-fixes accessibility issues in Canvas course content, using a specific verb (

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 explicitly says 'Run scan_course_content_accessibility first to see what will be fixed', creating a clear sequential workflow and distinguishing this from the scanner sibling. However, it doesn't explicitly list contrast scenarios or say when NOT to use it (e.g., if manual editing is preferred, or if content is locked). Still, the prerequisite guidance is strong.

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