audit

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real value: it explains the output shape (a summary line per kind, or a full Markdown report when save_to is set). It does not mention the cost/slowness caveat for keyboard and css checks, which lives only in the schema.

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?

Front-loaded with the core purpose and the kind list, then routing alternatives. Dense but every clause carries information; the kind parentheticals are the only mildly verbose portion.

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 correctly carries the return-value burden by describing both the summary-per-kind mode and the full-report mode. Combined with 100% schema coverage and explicit sibling routing, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3, but the description goes beyond the enum by explaining what each kind actually checks (tab order/focus, plugin/theme/host cost, CDN freshness) and clarifies that save_to swaps content for a returned path.

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?

States a specific verb (audit) plus the resource (page) and enumerates the exact check kinds, with parenthetical explanations of ambiguous ones like keyboard and resources. It is immediately distinguishable from sibling tools such as perf_trace, lighthouse, and cookie_audit.

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?

Explicitly routes the agent: 'For one deep look at load speed use perf_trace, for Lighthouse scores lighthouse.' It also instructs how to choose kinds and notes the default behavior, so the selection decision is fully specified rather than inferred.

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