accessibility_audit

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

With no annotations, the description carries the full burden. It discloses the use of axe-core and enumerates the return payload (score, violations, fixes), which is useful, but it does not explicitly state whether the audit is read-only, how failures are surfaced, or any rate limits or permission requirements.

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?

Two sentences, front-loaded with the core action, and every word adds value. No filler or redundancy.

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?

Despite lacking an output schema, the description preemptively explains what the tool returns (score, violations, fixes), covering the main agent needs. It does not mention error cases or edge conditions, but for a straightforward audit tool with only two parameters, it is reasonably complete.

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?

Both parameters are fully described in the schema (session_id, wcag_level with enum and default), so schema coverage is 100%. The description adds no additional parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 names a specific action ('Run a WCAG accessibility audit') and target ('current page of a session'), and uniquely identifies this as the accessibility-focused tool among siblings. It clearly distinguishes from tools like quick_scan or compare_screenshots.

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 implies the tool requires an active session ('current page of a session') and allows choosing WCAG level via the schema. However, it does not explicitly state when to prefer this over alternative tools like quick_scan, nor does it mention any prerequisites or exclusions.

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