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

Goes well beyond the annotations by disclosing latency (20–40s), default waiting behavior, the id-passing fallback when the wait expires, and the ten-minute result-caching rule — all operationally important facts an agent must know before invoking. The caching note is consistent with idempotentHint=false (a returned cached result is still not a guaranteed side-effect-free repeat) and contradicts nothing.

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?

Three tight sentences, front-loaded with what the audit covers and returns, then timing and the polling fallback. Every clause carries distinct information; no filler.

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 carries the return contract and does so adequately: grade, category scores, findings with fixes, plus the partial-result path via get_audit. Nothing an agent needs to call this tool correctly appears missing.

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 the baseline is 3; the description adds meaning by clarifying that waiting is the default and that timeout expiry produces an id to pass to get_audit, which mirrors and reinforces the wait/timeoutSeconds semantics rather than merely restating them.

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 ('runs SeeGeo's full audit of a domain') and enumerates the audited dimensions (crawler access for 16 AI bots, structured data, content extractability, etc.), then names the return artifact (grade A–F, category scores, findings with fixes). This clearly distinguishes it from crawler_check, get_audit, and list_audits.

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?

Explicitly routes the agent to get_audit when the wait times out and discloses the 10-minute re-audit cache behavior that selects against redundant calls. It does not explicitly contrast itself with crawler_check, so the alternative-selection guidance is strong but not exhaustive.

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