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

Goes well past the annotations by disclosing the return shape ({ label, labels }), the null-on-no-match behavior, the exact price (3 credits per successful call with a CAD cent conversion), and that schema-invalid input is rejected before billing. That billing-failure semantics is exactly the kind of operational detail an agent cannot infer elsewhere.

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 the action and constraint, then the return contract, then cost. No filler and nothing restated twice.

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 no output schema, the description correctly spends words defining the response shape and the null case. Pricing and pre-billing rejection complete the picture for a metered, read-only tool with only two fully documented parameters.

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 both parameters are already fully documented, and the description repeats the 2-20 / 1-40 bounds rather than adding to them. The one genuinely additive point is that the result is always one of the supplied labels or null, which is a return-value semantic more than a parameter one — baseline 3 applies.

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 precise verb and outcome: 'Picks one label from your list ... for a piece of text'. The phrase 'from your list' plus the 2-20 constraint clearly separates it from fixed-taxonomy siblings like sentiment or free-form extraction like entity-extract.

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?

Usage is implied by 'picks ONE label from your list', which implies closed-set single-label classification, but the description never says when to prefer this over sentiment, entity-extract or similarity, nor when not to use it. It supplies hard boundaries (2-20 labels) rather than selection guidance.

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