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

Annotations declare non-read-only, open-world, non-idempotent behavior, and the description adds real context beyond that: it consumes allowance (quota cost), wait:true may still return pollAfterMs so the caller should poll get_audit_status for up to 3 minutes, and it explicitly disclaims that a run proves indexing. Missing only details like whether results are stored/reused, but the operational caveats are unusually strong.

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, with the primary action, its cost, and its polling contract in the first sentence. Semicolon-chaining makes it slightly choppy to parse, but every clause carries routing or behavioral information and nothing is 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?

An output schema exists, so return shape needn't be explained. Given a 3-parameter tool with 100% schema coverage and rich annotations, the description still supplies the quota cost, async/polling contract, strategy tradeoff, and sibling routing rules an agent needs 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 coverage is 100%, so the baseline is 3. The description genuinely adds beyond the schema: the fact that wait:true 'may still return pollAfterMs' plus the follow-up polling window is not in the property description, and the quick-vs-full tradeoff is framed as an iteration/evidence decision rather than just a speed setting.

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?

Opens with a specific verb+resource ('Start a saved-site audit') and immediately distinguishes itself from the closest siblings: audit_url for unsaved URLs and get_seo_evidence for deployed-HTML evidence. An agent can route among audit_all_sites, audit_url, and run_audit from this text alone.

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 rules for the strategy enum ('quick for iteration and full for comprehensive evidence'), names the alternative for unsaved URLs ('Use audit_url only for performance on unsaved URLs'), and redirects to get_seo_evidence with exact parameters for indexing and canonical checks. Exclusions and alternatives are both covered.

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