system_one_classify

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds that ambiguous results require review, which is a useful behavioral cue beyond annotations. However, it does not elaborate on what 'review' entails or other potential side effects, so the added value is moderate.

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?

The description is a single, front-loaded sentence with no redundant words. It states the core action and a key behavioral caveat efficiently, earning a top score for conciseness and structure.

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 5 parameters, no output schema, and zero parameter descriptions in the schema, the description must carry substantial load. It leaves the purpose or intent of parameters like auto_accept and minimum_margin entirely unaddressed. An agent would not know how to set these values correctly, making the definition critically 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% for all 5 parameters. The description only implicitly references 'items' and 'classes' (via 'supplied items' and 'class catalog'), but says nothing about purpose, auto_accept, or minimum_margin. These parameters remain entirely unexplained, so the description fails to compensate for the schema's lack of descriptions.

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 clear verb and resource ('Classify supplied items against a shared class catalog'), and the name itself is unambiguous. It does not explicitly compare to sibling tools like system_one_decide or system_one_rerank, but the term 'classify' is self-explanatory and distinct enough.

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?

The phrase 'ambiguous results require review' implies a follow-up action but does not specify when to prefer this tool over siblings or mention any alternative tool names. It offers some contextual guidance but lacks explicit exclusions or routing logic, so an agent must infer usage.

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