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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds context annotations cannot express: generation 'does not publish' and draws against the recipe's credit caps. That credit-consumption and non-publishing disclosure is meaningful for a tool the annotations flag as a non-read-only action. It stops short of stating auth/permission requirements.

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, each doing distinct work: what is produced and its credit basis, what it deliberately does not do (publish), and the scope/type-match constraint. Front-loaded and free of padding.

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 explained, and the annotations cover the safety profile. But for a 4-parameter, 0%-coverage operation the description omits all parameter meaning and any relationship to the sibling prepare/approve/activate tools it is clearly part of, leaving the agent to reconstruct the workflow.

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%, so the description carries the full burden, yet it names none of the four required parameters. The only implicit semantics supplied is for automationId (it must reference the matching banner automation type). brandId, revision, and idempotencyKey — including the retry/idempotency contract implied by that last one — remain completely undocumented.

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 object ('Generate a paid review sample') and scopes itself against the ~19-strong family of sibling generate_*_automation_sample tools by declaring 'Only banner artwork'. The phrase 'paid review sample' is mildly non-standard jargon, but combined with 'using the saved recipe' an agent can identify the action and its narrow domain without opening the schema.

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 supplies a real precondition — the saved automation type must match this tool — which implicitly routes the agent away from the campaign/image/logo variants. However it never states when to call this versus prepare_banner_generator_automation, approve_automation_sample, or activate_banner_generator_automation, so the agent must infer the position in the generate→approve→activate workflow.

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