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

Annotations only declare non-readonly/idempotent/non-destructive; the description adds substantive behavior — credits are charged, a price mismatch aborts with price_changed and charges nothing, and a repeated requestId returns the same jobs with no second charge. It does not cover partial failure or what the returned jobs contain, which keeps it below a 5.

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?

It is short and front-loads the cost warning, but the middle sentence ("confirming the plan_kit price is accepted and only the lower remaining price is charged") is tangled and hard to parse. Several clauses pack multiple rules without separators, costing clarity per word.

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 credit-spending mutation with a nested options object, 20% schema coverage and no output schema, the credit/idempotency rules are well covered but the description never says what the call produces (final versions of the approved items? a job set?) or the shape of the response beyond price_changed. An agent can call it correctly but cannot predict the outcome.

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 20%, so the description must compensate, and it does for three of the five parameters: confirmCredits must exactly equal the item price, requestId is an idempotency key, and itemIds accepts the sentinel "approved". projectId is left unexplained and iconStyle/options is only partly contextualized via the plan_kit reference.

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 opens with the cost side effect ("Spends credits") but never states plainly what is produced — the title's "final assets" is the only clue. The credit language and the 'approved'/'plan_kit' references imply it finalizes approved items, so an agent can roughly infer the purpose, but the verb+resource is never made explicit.

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?

Preconditions are given (confirmCredits must equal the price, itemIds may be "approved", draft credits carry over), which implies this is the step after draft/approval. However, no sibling is named as an alternative and there is no explicit statement of when to use generate versus draft, plan_kit, or generate_sprite_sheet.

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