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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds meaningful non-obvious behavior: 'Free and starts nothing' confirms no credits are consumed and no job is created, and it notes the balance is returned alongside the estimate. It stops short of describing error conditions (e.g., unknown job_type) or the result shape, which keeps it from 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?

Three short sentences with no filler; the value proposition ('what a job costs in credits') comes first, followed by the safety note and the usage directive. The first sentence is a grammatical fragment covering three outputs at once, which slightly slows parsing but does not waste words.

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 two-parameter, read-only estimation tool with a nested params object and no output schema, the description does the necessary work: it names what is returned (cost in credits, balance, prompt notes) and states that nothing is started. The main residual gap is the lack of detail on how the open-ended params object should be populated beyond the schema's pointer to list_models.

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 100%, so 'job_type' and the nested 'params' object (with required prompt) are already documented. The description adds only a light hint that the prompt influences the returned notes, which is useful but thin given the nested, open-ended params object whose contents must be sourced from list_models. Baseline 3 is appropriate.

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 gives a specific verb (cost/price) and resource (a job in credits) plus two secondary outputs: the account balance and prompt hints/notes. It clearly separates the tool from 'generate' by framing it as a pre-flight check. It does not, however, distinguish itself from the sibling 'get_storyboard_price', leaving a minor ambiguity for storyboard workflows.

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 an explicit sequencing rule: 'Tell the user the price before you call generate,' which tells the agent both when to use it and how to act on the result. It omits any mention of alternatives such as get_storyboard_price or what to do if the balance is insufficient, so the coverage is clear but not exhaustive.

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