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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description layers on operationally important facts: robots.txt is respected, the optional judge step is rate-limited per day and degrades with a note, and results are grouped by priority with fixes and doc links. These are traits the annotations cannot express.

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?

Dense and front-loaded: routing rule first, examples second, exclusions last. It is longer than most descriptions, but nearly every clause carries routing or behavioral information; a small amount of overlap between the two 'use audit_site' mentions could be trimmed.

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?

An output schema exists, so return details need not be explained, and the description still summarizes the shape of results (failed rules by priority with fix and doc link, plus extracted page facts). Combined with the routing rules and safety context, an agent has everything needed 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%, so both parameters are already documented, including the judge rate limit and fallback note. The description only adds the instruction to 'pass the page address' and does not extend url semantics (e.g. bare-domain handling) beyond what the schema states, 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 and resource ('audit one page for SEO problems') and immediately scopes it to a single user-supplied address, with concrete request examples. It also names the sibling it is not (audit_site), so an agent can distinguish the two 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 explicit routing: one page address -> this tool, several pages or a whole site -> call audit_site once. It also names exclusions (private/local addresses, rankings or traffic, reading page text) and the rule classes that require audit_site (cross-page comparisons, sitemap reads).

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