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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description usefully reinforces this with "Nothing is charged and nothing is started." More valuable is the disclosure that it runs the same validation as the real generation calls, so invalid requests fail rather than return a partial estimate, and that a valid request's figure is exactly what gets charged. It doesn't cover error shapes or whether pricing can drift between estimate and execution.

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 tight sentences, front-loaded with what the tool returns, followed by accuracy guarantees and the no-side-effects statement. Every sentence adds a distinct fact with no repetition of the schema or annotations.

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 shape needn't be spelled out, and the description still summarizes the two fields an agent cares about. For a read-only, four-parameter tool with a nested options object, the description covers purpose, accuracy semantics, side-effect status and the scene-omission behavior without leaving anything an agent needs unresolved.

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 75%, so the baseline is 3, but the description adds genuine meaning: omitting scene prices every scene of the model, a multi-value behavior the schema does not convey. It also frames options explicitly as the options the caller intends to pass and notes they change the price. The prompt parameter is undocumented in both the schema and the description, which is the remaining gap.

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 a specific verb-and-resource pair ("Price a generation") and immediately defines the two return values: the credit charge for these options and whether the balance covers it. It also distinguishes itself from the siblings generate_3d and generate by explaining that it shares their validation and price calculation but does not start anything.

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 clearly states the pre-flight context ("before starting it") and points to the sibling tools whose pricing it mirrors, so an agent knows to call this before generate/generate_3d. It also gives a usage rule for an optional parameter ("Omit scene to price every scene of the model"). It stops short of explicit when-not-to-use guidance, for example telling the agent to call get_balance instead for a pure balance check.

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