Run a question set over many items

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

Annotations already declare readOnlyHint and openWorldHint; the description adds useful operational context beyond those: batch judging, per-item compact rows, per-question aggregates, and the ability to write full results to disk while only pulling back what matters. No contradiction with annotations.

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 sentences, front-loaded with the core behavior, and each clause earns its place. It explains what the tool returns, why it exists, and what workflow it supports without any 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 an 11-parameter tool with nested question schemas and no output schema, the description plus fully documented schema covers the main invocation and selection needs. It does not spell out the exact row layout or default behaviors, but those are largely covered by the schema.

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 baseline is 3. The description maps at a high level to filter/sort/save_path/include_rows concepts but does not add parameter-specific meaning beyond what the input schema already provides.

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?

States a specific behavior: 'Judge every item in a list' and defines the return shape ('one compact row per item, plus per-question aggregates'). It clearly differentiates from single-item siblings like jev_eval and jev_ask by emphasizing multi-item mapping and scale.

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?

Gives clear context for when this tool is the right choice: 'triage and ranking at a scale where reading each item into context is the expensive part', with filter/sort/disk-write options to avoid pulling everything into context. It does not explicitly name when-not or alternative tools, so it stops short of a 5.

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