jev_judge

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

With no annotations, the description carries the full burden. It discloses key behaviors: it only evaluates supplied evidence, returns calibrated probabilities, and rejects generative requests. This gives the agent a clear behavioral model, though it doesn't cover potential errors or rate limits.

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?

Three sentences with no filler. The core purpose is front-loaded, and each sentence adds distinct information: what it does, what it rejects, and a key behavioral caveat.

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?

The tool has nested objects and 4 parameters, but the description covers only the general behavior. It doesn't explain the structure of questions, the role of state, or client metadata. For a tool that requires evidence, it doesn't specify where evidence goes.

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%, so the description must compensate. It hints at questions holding propositions and evidence being supplied, but it doesn't explain state, client, or use_cache. This leaves most parameters underspecified.

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: asking one evidence-grounded yes/no proposition per question and receiving calibrated probabilities. It also mentions what it rejects. However, it does not explicitly differentiate from sibling judgment tools, relying on 'generic' to imply its role.

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 implies usage by calling it a 'generic bounded judgment primitive' and notes it rejects generative requests, which is a when-not. It does not provide explicit guidance on when to prefer this over sibling tools like jev_assess_risk or jev_triage_failure.

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