a11y_audit_dom

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

With no annotations, the description carries the full burden and does so well: it discloses the Playwright/Chromium runtime dependency with the exact install command, describes what each check measures (alpha compositing, 24×24 targets), and states that findings include remediation. It stops short of describing failure modes, rate limits, or output shape.

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?

A single dense paragraph that front-loads the primary purpose before the parenthetical criterion list and ends with the prerequisite. The criterion parentheticals are information-rich, though slightly heavy; every clause earns its place.

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?

For a 3-param tool with no output schema and no annotations, the description covers purpose, scope, checks, remediation output, and runtime prerequisites well. The gap is parameter-level semantics, which is the one area left thin.

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 33% – url and lang have no descriptions, and only timeout is documented in the schema. The description adds nothing about the parameters (no URL format, no explanation of the lang enum's effect on locale-specific checks), so it fails to compensate for the coverage gap.

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?

Names a specific verb+resource ('deep RENDERED WCAG audit via local Playwright/Chromium') and enumerates the exact checks performed with WCAG criterion numbers. It also implicitly distinguishes itself from a11y_audit_url by describing 'rendered versions of the static checks'.

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 'Deep RENDERED' framing and the 'rendered versions of the static checks' phrase imply this is the heavier Playwright-based counterpart to the static a11y_audit_url, but no explicit when-to-use or when-not-to-use guidance is given. An agent must infer the routing from the adjective 'deep'.

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