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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true and idempotentHint=false, and the description reinforces the safety profile ('reads or computes only and changes nothing'). The genuinely additive context is the billing model — $0.01/call via x402 USDC or card key through /credits, failed calls free, repeats not free — which explains the non-idempotent flag and warns against retry loops; a 3 rather than higher because cost is the only behavioral trait it expands on.

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 front-loaded with what is audited and what is returned, then usage cases, then pricing and safety. It is a dense paragraph with no filler sentences, though the pricing/safety tail and the component list make it long enough that a sentence break would improve scanability.

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?

There is no output schema, so the description carries the full burden of describing results, and it does: rule, impact, elements and fix link for accessibility, FCP/LCP/layout shift and page weight for speed, plus an overall score and top issues. Cost, payment path, failure policy and the read-only guarantee round out everything an agent needs 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?

With only one parameter at 100% schema coverage, the schema already documents 'Absolute http(s) URL of the page to audit'. The description adds a worked example (url=https://www.wikipedia.org/) and the constraint that only one URL per call is audited ('one URL', 'single load'), which is useful but marginal, so the high-coverage baseline of 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?

The description names a concrete verb and resource ('Full website audit of one URL') and enumerates the four audit dimensions (WCAG 2.1 A/AA via axe-core, page speed/weight, on-page SEO, HTTP security headers) plus the composite output ('one overall score and the top issues'). It implicitly separates itself from narrower siblings like seo_audit or http_security_headers by promising everything 'from a single load in a real browser', but it never names those alternatives explicitly.

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?

Three concrete use cases are given: a site or client report, a pre-launch check, and competitor comparison. That is clear positive guidance, but there is no when-not-to-use guidance and no routing to the single-purpose siblings (seo_audit, http_security_headers) for users who only need one dimension.

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