audit_accessibility

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

With no annotations, the description must carry the burden of behavioral disclosure. It indicates the tool returns violations grouped by impact level but does not detail potential side effects (none expected for a read-only audit), performance impact, or permission requirements. The behavior is adequately implied but not fully transparent.

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 two sentences long, no redundancy, and the most critical information (what the tool does) is front-loaded. Every sentence serves a purpose.

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 three parameters, no output schema, and no annotations, the description covers the core functionality well. It could be slightly more complete by mentioning that the audit follows WCAG standards or that output includes actionable details, but it suffices for context.

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 only 33% (only 'scope' has a description). The description adds meaningful context for 'scope' by explaining its purpose. However, it does not elaborate on the 'impact' enum values or the 'standard' options, leaving room for ambiguity despite the schema providing enums and defaults.

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 it runs an axe-core WCAG accessibility audit on the current page, specifying the verb ('Run'), resource ('WCAG accessibility audit'), and scope ('on the current page'). It distinguishes itself from sibling tools like 'get_page_performance' and 'measure_coverage' by focusing specifically on accessibility.

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 advises using the 'scope' parameter to limit the audit to a specific DOM subtree, providing clear usage guidance. However, it does not mention when not to use the tool or suggest alternatives, though no direct alternative exists among siblings.

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