campaign_audit

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

The readOnlyHint, idempotentHint, and openWorldHint annotations already establish safety and network behavior. The description adds that the tool gathers baselines across four report levels, which is useful context, but it does not explain whether all four are returned together, whether anything persists, or any rate-limit/auth nuance. With annotations covering the safety profile, this is adequate but not rich.

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?

The description is a single front-loaded sentence with no filler. It is appropriately sized and immediately states the resource scope.

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 a nine-parameter tool with an output schema and safety annotations, the description gives only the broad collection scope. It leaves the meaning of 'baseline', the aggregation behavior, and the choice against sibling report tools implicit, so it is only partially complete for tool selection.

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 schema documents all nine parameters including profile, adAccountId, timeRange, filters, and pagination. The description adds no parameter-level detail, so it neither helps nor hurts beyond the schema; the baseline is 3.

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 uses a specific verb ('Collect') and names the four report domains whose baselines are gathered. It is distinguishable from single-report siblings like campaign_report because it lists all four levels, though it does not define what a 'baseline' contains.

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?

There is no explicit when-to-use guidance, no exclusions, and no mention of sibling report tools or optimization_baseline. An agent can infer it is for baseline collection, but the description does not say when this tool is preferable to campaign_report, ad_group_report, keyword_report, or search_term_report.

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