Get atomic judgments on supplied text or JSON by running custom typed questions (noul, choice, score) in parallel.
Typed atomic judgments over supplied text. Use only if a specific recipe does not fit.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Override, default jev-latest | |
| state | Yes | Shared state to judge: text or JSON | |
| questions | Yes | Named noul, choice, and score questions evaluated in parallel |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds no behavioral details beyond that – no mention of evaluation process, parallelism, or side effects. It doesn't contradict annotations, but it contributes little extra value on top of them.
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 with zero waste. The purpose is front-loaded, and the usage condition follows immediately. Every word earns its place; it's a model of conciseness.
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 complexity of the nested question schema, the description is thin. It provides the crucial fallback guidance, but it doesn't explain what the tool returns (no output schema) or give examples of how to structure questions. The schema is self-descriptive, so it's adequate but not robust; an agent would need to rely heavily on 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%, with detailed descriptions for 'state', 'questions', and 'model'. The tool description adds no parameter-specific meaning, so the baseline of 3 applies – the schema does the heavy lifting.
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 'Typed atomic judgments over supplied text' – a verb and resource – but 'typed atomic' is domain jargon and doesn't clarify the three question types (noul, choice, score) that the schema defines. The fallback note 'Use only if a specific recipe does not fit' hints at differentiation from siblings, but the core purpose remains ambiguous without schema inspection.
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 explicitly says 'Use only if a specific recipe does not fit', which clearly establishes the condition for use and implies alternatives (specific recipes). It doesn't name the sibling tools, but the sibling list provides enough context for an agent to infer which tools are the 'recipes'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.