classify

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

With no annotations, the description carries the behavioral burden and does it well: it discloses that exactly one category is assigned, that confidence is calibrated, and that the full probability distribution over labels is returned. It omits edge-case behavior when neither labels nor criteria are supplied, but core behavior is transparent.

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?

Two tight blocks with no filler: the primary action leads, parameter guidance follows, and the return contract closes the description. Every sentence adds information.

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 5-parameter tool with no annotations and 0% schema coverage, too much is left unresolved: whether labels or criteria are mandatory despite the schema only requiring state, how instructions affect behavior, what model defaults to, and what happens if neither labels nor criteria is provided. The output schema covers return shape, but calling semantics remain incomplete.

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 description coverage is 0%, so the description must compensate. It gives meaning to labels and criteria, and implies state is the thing being classified, but it never explains the model or instructions parameters, and does not define what kinds of values state may take.

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 states a specific verb and resource: 'Assign the single best category to a state' and narrows the task to 'one choice question'. It makes the classification purpose clear, though it does not explicitly contrast this tool with siblings like decide or score.

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 actionable guidance on parameter selection: 'Provide either labels ... or criteria', and even notes that criteria is 'more accurate'. However, it does not say when to prefer classify over sibling tools, and it provides no exclusions or alternative tool routing.

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