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

Annotations cover the safety profile (idempotent, non-destructive, open-world), so the description's added value is the cost and side-effect context: calling this consumes 'credit caps' and it explicitly 'does not publish', which tells the agent this is a billable dry-run. It stops short of describing async behavior, retries, or what the sample returns.

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 compact sentences with the core action and the no-publish constraint front-loaded. The final clause ('the saved automation type must match this tool') is terse to the point of being cryptic, which costs it a point.

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 carry the safety profile. The remaining gap is that a mutation with four required, undocumented parameters omits the meaning of revision and idempotencyKey, leaving an agent unable to construct a fully correct call from text alone.

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 four required parameters, so the description carries the burden but does not meet it. 'The saved recipe' loosely implies automationId and the type-match sentence hints at a precondition, but brandId, revision, and idempotencyKey are never explained despite being required.

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 outcome ('Generate a paid review sample using the saved recipe') and scopes the resource ('Only replacement image backgrounds'), which distinguishes it from the many sibling generate_*_automation_sample tools. It is clear what it produces, though 'sample' remains somewhat abstract without a concrete notion of what the sample 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?

It gives two useful conditions: 'Does not publish' (routes the agent toward preview rather than activation) and 'the saved automation type must match this tool' (a precondition). However, it never explains the relationship to the surrounding prepare_/activate_/resume_/update_image_backgrounds_automation family, so the when-to-use-vs-alternatives guidance is only implied.

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