evaluate
Answer typed noul, choice, or score questions about a given state with probability distributions and confidence for routing, classification, scoring, and escalation gating.
Instructions
Jev-compatible decision call. Send a state and typed questions (noul/choice/score); get back answers with probability distributions and confidence. Use for routing, classification, scoring, escalation gating — not for open-ended generation.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"state": "<state>",
"questions": "<questions>"
},
"name": "evaluate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | Text or JSON the questions are about | |
| questions | Yes | Map questionId to a Jev question. Optional conditions v1 defines typed fact extractors, ordered local rules, and a default outcome. Output probabilities are composed from fact marginals under an independence assumption. |