Accessibility check

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and live-environment behavior are covered by structured data. The description adds useful scope (which audit rules run) and states that offending elements come back with selectors, but it does not say what happens on a page with no failures, whether the audit is static or requires rendering/loading time, or whether it is scoped to the whole page or the current viewport.

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 with no filler: the audit scope and the four checks come first, and the return content is stated second. Every clause carries information an agent needs.

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?

With no output schema, the description carries the burden of describing results and does so at a high level ('offending elements with selectors'). It falls slightly short on the empty/clean-result case and on whether results include severity or counts, which matters for an audit tool an agent may need to report on.

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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description is consistent with a parameterless call that always targets the current page.

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 names a specific verb ('Audits') and resource ('the live page') and enumerates the four concrete checks performed (contrast failures, missing accessible names, skipped heading levels, undersized touch targets). That is far more specific than a generic 'check accessibility', though it does not name or differentiate itself from nearby inspection siblings such as inspect_element or get_diagnostics.

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?

Usage is only implied: 'the live page' signals it operates on whatever page is currently loaded, so an agent can infer it must navigate first. There is no explicit when-to-use, when-not-to-use, or pointer to an alternative for narrower element-level checks, leaving routing decisions to inference.

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