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

Annotations only cover the safety profile (readOnly, non-destructive, open-world); the description goes well beyond them by enumerating the full return payload, disclosing the data_gaps list semantics ("what's missing and why — Search Console always appears here"), and stating that unavailable backlinks come with an explanation. The explicit "this never writes prose for you" boundary is exactly the kind of behavioral trait 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?

One dense paragraph with the essential action front-loaded and no filler sentences; every clause carries information. The long mid-sentence enumeration of return fields is heavy to scan, but with no output schema it is doing necessary work.

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?

For an async-poll tool with no output schema, the description supplies the missing return contract in detail, covers both the running and completed states, and flags the known always-present data gap. An agent can call this correctly and interpret the result without opening anything else.

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 audit_id parameter is already documented as "The id returned by start_prospect_audit." The description adds no parameter-level detail (no format, no staleness or reuse guidance), 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+resource ("Poll a prospect audit") and immediately scopes it as a status/result reader for an async job, which cleanly separates it from start_prospect_audit, list_prospect_audits, and the generic get_audit/get_audit_report siblings. The return enumeration makes the resource unambiguous.

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?

"Poll" plus the schema note that audit_id comes from start_prospect_audit establishes the trigger and the expected repeat-call pattern, and the closing sentence draws a clear responsibility boundary (the caller writes the prose, not this tool). It stops short of explicit when-not-to-use guidance or polling cadence, so it is clear but not exhaustive.

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