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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the trailing 'Read-only' adds nothing. The description does add real diagnostic context — that results are judged against the account's own conversion volume rather than fixed industry thresholds — but says nothing about permissions, cost/latency, or how findings are ranked.

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?

Two dense, front-loaded sentences that enumerate actionable finding types with no filler. The appended 'Tools revision: 5c9bea8f' line is pure noise for an agent deciding whether to call the tool.

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-value explanation is not required, and annotations cover the safety profile. What is missing is any guidance on the runtime knobs that materially change the result set (detail, max_findings, days), leaving an agent to guess at cost and coverage for a five-parameter audit.

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 0% across five parameters, and the description explains none of them: the lookback window (days), the summary-vs-full verbosity (detail), the render mode, or the finding cap (max_findings) are all left to inference. Only 'conversion volume' loosely hints that a historical period is involved.

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 gives a specific verb and resource ('audit bidding strategies against the account's own conversion volume') and enumerates the exact finding classes it produces, which makes it distinguishable from generic siblings like full_audit or account_health_score. It stops short of naming a sibling it should be preferred over, so it lands just below a 5.

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?

Usage is implied by the enumerated problem scenarios (manual bidding with enough data, unrealistic CPA/ROAS targets, stuck learning, low-volume campaigns), which tells an agent this is a diagnostic to run when those symptoms are suspected. There is no explicit when-not guidance and no pointer to alternatives such as full_audit, conversion_setup_audit, or budget_pacing when the issue is not bid-strategy related.

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