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

Annotations only mark non-readOnly/non-idempotent/non-destructive, which the description supersedes with real behavior: 1 credit per answered question per text, blanks and duplicate texts free, chunking into internal calls of 40, and limits (no math/counting/dates, English best). That is far beyond what the annotations provide.

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?

Front-loaded with the core action and then the when-to-use rule, cost, and limits in descending priority. Dense but largely earned; the cost-and-limits tail is slightly packed into long sentences, costing a point.

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?

With an output schema present, return values need no explanation, and the description still covers the caller's real unknowns: credit cost, free cases, chunking, and the model's blind spots. An agent has everything needed to call this correctly.

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 already 100%, so baseline is 3; the description adds meaning the schema lacks by constraining questions ('each question needs its own definition of yes inside it') and noting the 10-question cap ties to per-text cost. It does not explain the api_key parameter's behavior beyond what the schema says.

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 (Ask) and resource (up to 10 yes/no questions over a batch of texts) with the exact output form: one probability per question per text, not generated prose. This cleanly separates it from hunch_ask (single question) and hunch_score/pick siblings.

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?

Gives an explicit selection rule with a threshold ('Prefer it to judging the texts yourself once there are more than about 25') plus alternatives it beats ('a fraction of the tokens of separate calls'). Concrete examples of batched judgments on one ticket make the intended use unambiguous.

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