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

Beyond the annotations, the description discloses the financial side effect (credits are spent), the failure mode when the price changed (nothing charged, price_changed returned), and the retry contract (same requestId returns the same jobs at no charge). This is meaningful added context on a mutation whose annotations only say it is non-destructive and idempotent; it stops short of auth or rate-limit context.

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?

Four short, front-loaded sentences with no waste, and the cost consequence leads. The telegraphic fragments ('itemIds may be "approved"') drop context about what "approved" expands to, which costs a little clarity for the brevity gained.

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 generator with five parameters, no output schema, and 20% schema coverage, the description covers cost, price-mismatch, and idempotency well but omits what is actually produced (jobs are only alluded to), what projectId scopes, and how 'approved' interacts with the itemIds cap of 40.

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 coverage is only 20%, so the description must carry the load, and it does for three of the four required params: confirmCredits as an exact price match, requestId as an idempotency key, and itemIds accepting the literal "approved". projectId and the options object remain undocumented in prose (options is only covered by the schema's own nested description).

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 'Spends credits' rather than stating that it generates final assets; the actual action is only recoverable from the name and title. It is preoccupied with cost and idempotency mechanics, so an agent learns the consequence of the call faster than its purpose, and no sibling (draft, plan_kit, approve) is contrasted.

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 states a hard precondition ('confirmCredits must equal the price of the items') but never says when to call this instead of draft, plan_kit, or approve, nor what must happen first (planning, approval). There are no exclusions or alternative routing for an agent to follow.

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