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

With no annotations, the description carries the full burden and does substantial work: it declares this makes no site changes, warns the output contains placeholders needing real values, disclaims citation guarantees, and documents an unusual operational trait (payment challenge and credentials bound to the GET URL, not mcp://, with retry using identical authorized arguments). It still omits rate limits, failure modes beyond payment, and caching behavior, so it falls short of exhaustive.

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?

Purpose and the deep_audit alternative are front-loaded, and each sentence adds a distinct caveat or constraint. The closing payment/credential/retry sentence is operationally important but tacked on and reads more like a troubleshooting note than part of a clean structure.

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 still names what is returned (deterministic paste-ready JSON-LD template, live structured-data gap diff, ranked fixes) and flags the placeholder caveat, which is the key thing an agent must convey to a user. A three-parameter, single-required-param tool is adequately covered, though return-format and error-handling details remain thin.

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 site, city, and vertical are already fully documented, including the med-spas fallback behavior for vertical. The description adds no parameter-level syntax or format detail beyond the schema, so the 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 and resource (analyze a public business site, return a JSON-LD template plus gap diff and ranked fixes) and explicitly names the sibling it is not (deep_audit). An agent can distinguish it from deep_audit and the other audit tools without opening a 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 an explicit alternative and the condition that selects it: use deep_audit when the call must also return company, technology, contact, and DNS/email evidence. It does not state the inverse trigger ('use this when you only need JSON-LD') or rule out other audit siblings, but the routing guidance is concrete rather than implied.

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