Measure question variants against labeled examples

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

Annotations already provide readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds no extra behavioral traits such as rate limits, auth needs, or side effects; the 'nearly free' remark hints at cost but is not a full disclosure. With annotations present, a 3 is appropriate because the description does not contradict and offers only marginal extra context.

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 three sentences, each with a distinct purpose: the first enumerates the output metrics, the second gives usage timing, and the third explains the efficiency of passing multiple variants. There is no filler, and the core action is front-loaded.

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 has no output schema, the description appropriately enumerates the main output components (accuracy, Brier, ECE, AUC, threshold sweep, abstention curve, worst misses). It also covers the key workflow hint about evaluating before thresholding. However, it does not explain the distinction between inline items and dataset_path or the meaning of noul/choice/score types—though those are covered by the schema, so the description remains largely complete.

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 input schema already explains each parameter fully. The description adds a high-level tie to 'one or more wordings' (variants) and 'labeled items' (items/dataset_path) but does not provide any new parameter-specific semantics. Baseline 3 is correct.

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 action (score question variants against labeled items) and enumerates the outputs (accuracy, calibration, threshold sweep, abstention curve, worst misses), so the purpose is unambiguous. However, it does not explicitly distinguish this tool from siblings jev_map and jev_ask, so it earns 4 rather than 5.

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 description gives clear usage timing: 'Run this before hard-coding any threshold, and rerun it after changing wording or model version.' It also notes that passing multiple variants is 'nearly free,' implying a best practice. It does not mention when NOT to use the tool or point to alternatives, which prevents a 5.

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