change_history

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds meaningful behavioral context by noting that Google retains at most 30 days of change history, which sets expectations about data availability and the limit of the days parameter.

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 two tight sentences that pack in the core data model, use cases, and a retention caveat without fluff. Every clause adds value.

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?

While the description captures the purpose and the 30-day retention constraint, it fails to guide invocation: it omits parameter semantics, required fields, defaults, and filtering behavior. The presence of an output schema helps, but the input side remains under-specified for a tool with 5 parameters.

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 does not name or explain parameters such as customer_id, days, limit, campaign_id, or exclude_api. It only hints at the 30-day window and client types, giving limited indirect meaning but not enough to compensate for the lack of schema descriptions.

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 clearly explains what the tool does: it returns who changed what, when, from which client, and which fields changed. It also differentiates the tool by framing it as answering 'why did performance shift' and 'was this setting deliberate', which distinguishes it from performance and audit-related siblings.

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 practical usage context by tying the tool to diagnosing performance shifts and determining whether a setting was deliberately changed. It does not explicitly name alternatives or state when not to use it, but the use cases are clear enough for an agent.

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