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

Annotations already declare readOnly/non-destructive/closed-world, so the bar is lower. The description still adds meaningful behavioral context: it reads a stored result and explicitly does not re-run the audit, which prevents an agent from assuming freshness and is the single most important caveat here.

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, front-loaded with the use case, followed by the scope of data and the read-vs-rerun caveat. No wasted words.

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 enumerated audit categories serve as a useful preview of what the result contains, filling the biggest gap. Minor remaining omission is any hint about data freshness or how the audit is populated, but overall the definition is sufficient 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 description coverage is 100% and the single optional 'brand' parameter is fully documented in the schema (name or id, empty to use the sole brand, list_brands to enumerate). The description contributes nothing about the parameter, so baseline 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?

States a specific verb+resource (show the brand's stored site audit) and enumerates the exact dimensions covered: crawler access, llms.txt, schema, meta tags, server-rendered copy, about and pricing pages. This clearly distinguishes it from the sibling check_* / validate_* tools that run live checks.

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 an explicit trigger ('when someone asks whether AI engines can read their own brand's site') and clarifies the read-vs-run boundary. It does not name a specific alternative sibling (e.g., check_ai_crawler_access) for the case where a fresh audit is wanted, so routing is inferred rather than explicit.

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