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

Annotations already declare a read-only, open-world, non-destructive operation, yet the description adds substantial context beyond them: 15-minute result caching, determinism with no AI model and no account required, a 30-day shareable reportUrl that can be null, errors returned as one plain sentence, and an explicit data-recording policy (domain and path, never query string or IP). This is exactly the kind of operational and privacy detail annotations cannot convey.

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 purpose and usage before drilling into return shape, and nearly every sentence carries actionable information. It is dense and partly run-on, with output-structure detail packed into long sentences, but nothing is genuinely redundant.

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?

No output schema exists, so the return-value description (summary, reportUrl, result.url, status, per-layer scores, problems with check id/severity/evidence, passed and notApplicable) is necessary and fully supplied. Combined with caching, privacy, and limitation disclosures, an agent has everything needed to call this correctly and set expectations.

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 both url and brandName are already documented in the schema, including the brandName-to-organization-identity-check relationship. The description adds no format, constraint, or edge-case detail about the parameters themselves beyond noting that result.url shows where the page landed. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ('SEO audit of one web page') and immediately scopes it to technical SEO plus AI search readiness, then enumerates the exact check families (indexing, title/meta, headings, JSON-LD schema, links, alt text, AI readiness). That enumeration positions it clearly against narrower siblings such as check_agent_readiness, check_robots_sitemap_llms_txt or check_ai_crawler_access without needing to name them.

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 explicit when-to-use triggers ('the person asks for an SEO or website audit of a page, how a page does in search or AI answers, or what to fix first') and explicit when-not coverage ('do not cover rankings, keyword volumes, backlinks or how AI answers mention the brand'). It stops short of naming which sibling to route to for those excluded needs, leaving the agent to infer the alternative.

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