target_cpa_recommendation_apply_preview

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the "explicit maximum" constraint, but it does not explain preview validation behavior or how a preview differs from an actual apply beyond 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?

The description is a single front-loaded sentence with no wasted words. It communicates the core action and constraint efficiently.

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 six-parameter tool with only 33% schema description coverage, the description is too sparse. Output schema and annotations help with return values and safety, but key parameter semantics and usage routing are still missing.

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 only 33%, so the description would need to compensate for several undocumented parameters. It only loosely maps "one recommendation" to recommendationId and "explicit maximum" to maximumAmount, leaving appliedAmount, profile, adAccountId, promotedObjectId, and the appliedAmount-vs-maximumAmount relationship unclear.

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 and resource: preview applying one target-CPA recommendation. It is distinguishable from the dismiss sibling by "apply," though it does not explicitly name alternatives or contrast with the non-preview apply path.

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 word "Preview" implies a dry-run before applying, which gives some usage context. However, it does not explicitly say when to use this versus target_cpa_recommendations, target_cpa_recommendation_dismiss_preview, or an actual apply operation.

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