audit_campaign

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

Annotations already declare readOnlyHint=true, and the description aligns with that by framing the operation as a review. It additionally discloses a non-obvious behavioral trait: no performance data is consulted, which is why the tool is safe for accounts without history. openWorldHint is not contradicted.

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 sentences, front-loaded with the purpose, followed by a compact checklist of review areas and a critical constraint. Every clause earns its place and there is no filler or repetition.

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?

The description covers the review scope, the key data-absence constraint, and the environments where it works, while an output schema exists to document returns. The only notable gap is the undocumented optional 'today' parameter, which is minor given its default and optionality.

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% and the description provides no parameter-level guidance beyond the operation itself. customer_id and campaign_id are self-explanatory, but the optional 'today' parameter and any format requirements are left entirely to the schema.

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 opens with a specific verb and resource — 'Structural review of a campaign' — and enumerates concrete findings such as targeting gaps, Display expansion left on, thin RSAs, and budget-to-bid mismatch. It also differentiates itself from performance-focused siblings by explicitly stating it uses no performance data.

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?

It clearly states when the tool is appropriate: because it uses no performance data, it works on test accounts and brand-new campaigns. It does not explicitly name sibling alternatives or include a when-not-to-use clause, but the context is clear enough for an agent to choose it over performance-dependent tools like keyword_performance or geo_performance.

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