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

Annotations already establish readOnly/idempotent/non-destructive safety. The description adds genuinely useful behavioral context beyond that: the async nature (returns a runId, not a result), the polling loop requirement, cached-result handling, and the critical 'nothing starts without budget' behavior. No contradiction with the annotations.

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 is front-loaded in the first sentence, and every sentence earns its place: scope, parameter gating, budget exception, and the polling workflow. It is dense but not bloated; it packs multiple distinct topics into a single block, which is the only structural weakness.

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 start-tool with no output schema, the description covers what an agent needs: what is started, when it won't start, parameter prerequisites, how to retrieve results (poll get_audit_report with runId), and caching semantics. Minor gaps remain: the term 'paid engines'/'paid budget' is never defined, and the individual free tools are referenced generically rather than by name.

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 maps city→AI visibility and placeId→local rank, but these largely duplicate the schema's own parameter descriptions ('Needed for the AI visibility check', 'Needed for the local rank grid'). The only incremental value is stating that businessName and state are for 'accurate identification', which is marginal over the 100% schema coverage.

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?

The description states a specific verb-resource pair ('Start the full visibility audit') and enumerates exactly what the audit encompasses: site speed, agent readiness, and Open Service Profile conformance. This clearly distinguishes it from the sibling single-purpose tools (check_site_speed, check_ai_visibility, etc.) since it is the umbrella audit that subsumes them.

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?

The description gives explicit when-to-use guidance: use this for a full multi-part audit, and explicitly excludes the use case ('If the paid budget cannot cover this request, nothing starts; use the individual free tools'). It also provides workflow guidance on polling vs. cached results. It does not individually name which sibling is preferred for which condition, but the alternative ('individual free tools') is concrete enough.

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