Batch Evaluation

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

With annotations providing no meaningful hints (all false), the description carries the full burden and delivers: pricing ($0.10), independent COMMIT/NO_COMMIT verdicts per item, same logic as single-item tools, results returned in input order, a shared batch_id, and no enforced size limit. This is comprehensive behavioral disclosure.

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 dense paragraph but every sentence earns its place: cost, behavior, item format, policy defaults, return format, and usage recommendation. It is efficiently front-loaded with the pricing and primary action.

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?

Given the tool's complexity (batch evaluation, mixed policies, paid action), the description covers all necessary context: how items are structured, which policies are supported, independent verdicts, return format, and cost. It is fully self-sufficient even with the output schema present.

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?

Although schema coverage is 100%, the description enriches parameter understanding by detailing the item structure, the default policy value, and listing allowed policy names (default, strict, anti_jailbreak, safety, content_quality). It also clarifies the output shape (results and batch_id), going well beyond the schema's basic 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 clearly states the tool's function: 'Evaluates a list of items in one call' with a specific verb and resource. It also distinguishes itself from siblings by explicitly positioning it as the batch alternative to multiple single-item evaluate_* calls.

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?

Explicit guidance is provided: 'Use this instead of multiple single-item evaluate_* calls when checking several responses — optionally against different policies — in one priced call.' This clearly states when to use the tool and contrasts it with alternatives.

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