classify

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds that the operation is deterministic (System One calculus) and specifies return values (top label, probability distribution, margin), which is valuable since no output schema exists. It does not cover error behavior or rate limits, but the annotation set carries the safety profile.

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 sentences, front-loaded with purpose, followed by routing guidance and return values. Every sentence contributes new information without repetition or filler.

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 tool with no output schema, the description usefully states what is returned (top class label, probability distribution, classification margin). Annotations cover safety and idempotency, and the schema covers parameters fully. Minor gaps around state_pack semantics and error handling remain, but the core needs are met.

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 100%, so the schema itself documents all five parameters. The description mentions the target types broadly but adds no syntax, constraints, or meaning beyond what the schema already provides. 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 states a specific verb (assign semantic categorical labels) and resource scope (entity, visual_state, task, snapshot) and names the sibling tool it replaces (ask_choice). An agent can distinguish it from ask_choice and ask_score without opening the schema.

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 when-to-use rule: assign predefined taxonomy labels rather than selecting among runtime decision alternatives, and names the alternative tool ask_choice. This is clear routing guidance with an implicit when-not condition.

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