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

Annotations already declare non-destructive, open-world, idempotent behavior, so the bar is lower, and the description still adds genuinely new context: the operation consumes credit caps, it does not publish, and the saved automation must be the matching type. It omits idempotency/retry semantics despite the idempotencyKey parameter, so it is not exhaustive.

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?

Three short sentences, front-loaded with the action and outcome, with no filler. The final clause is slightly terse/ambiguous but still earns its place by encoding a hard precondition.

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 values need not be described, and annotations cover the safety profile. However, for a four-required-parameter mutation in a 20-plus sibling family, the description leaves parameter meaning and sibling routing gaps that an agent must guess at.

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 all four parameters, so the description carries the full burden and largely fails: brandId, revision, and idempotencyKey are never explained. Only an oblique hint exists that automationId must reference a saved automation of the matching type.

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?

States a specific verb and resource ('Generate a paid review sample using the saved recipe') and scopes it ('Only advertising artwork'), which separates it from the surrounding non-sample siblings. It does not name the rescue path relative to prepare_/activate_/resume_ variants of the same family, so sibling differentiation is only partial.

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?

Gives one real precondition ('the saved automation type must match this tool') and clarifies the outcome ('Does not publish'), which implies this is a preview/review step. It never states when to call this instead of prepare_ad_creative_builder_automation or activate_ad_creative_builder_automation, so the workflow position is left to inference.

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