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

Annotations already declare readOnly, openWorld and non-destructive, and the description still adds real behavior: it fetches only the given page plus robots.txt and sitemap, honors robots.txt, returns category scores and prioritized fixes in English, and caches results for the same page for up to 6 hours. The performance test's cost is also surfaced as an up-to-30-second addition.

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 trigger and exclusions in the first and last sentences, with scope and caching facts in between. Dense but mostly earning its place; the long mid-sentence feature list is the only slightly run-on element.

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?

Covers trigger, exclusions, fetch scope, robots compliance, latency cost, caching, and output language, and an output schema already documents return structure. Nothing an agent needs in order to call this correctly is missing.

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 100%, so the schema already documents all three parameters, including PageSpeed's 30-second cost and the ISO 639-1 language format. The description echoes these (language versions for export markets, mobile performance via PageSpeed Insights) but adds no syntax or default detail beyond the schema, which is the expected baseline.

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 and resource (marketing audit of a public website) and enumerates the concrete dimensions checked: technical SEO, mobile performance, lead conversion, trust signals, analytics tags, and language versions. It explicitly names the sibling it is not (check_ai_search_readiness), so an agent can route without opening either schema.

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?

Gives a positive trigger ('when the user wants a marketing audit of a public website, especially a B2B, manufacturer, exporter or service-business site') plus three explicit exclusions: AI crawler/search questions, login-gated pages, and monitoring sites the user isn't evaluating. The alternative for the AI case is named directly.

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