evaluate_decision
Evaluate context, diffs, logs, or planning options and receive calibrated probabilities for binary, categorical, or scoring questions—before committing to lengthy plans or edits.
Instructions
Zero-token-output decision engine powered by TypeSafe Jev. Evaluates context, code diffs, logs, or planning options and returns calibrated probabilities. Use this BEFORE generating long reasoning plans or multi-file edits to pick optimal paths.
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>",
"question": "<question>",
"type": "<type>",
"criteria": "<criteria>"
},
"name": "evaluate_decision"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | Decision format: 'noul' (binary yes/no probability), 'choice' (categorical distribution), or 'score' (ordered rubric). | |
| state | Yes | The context, code diff, error log, or task description to evaluate. | |
| apiKey | No | Optional OpenRouter API key. If omitted, the OPENROUTER_API_KEY environment variable will be used. | |
| criteria | Yes | Criteria map: for 'noul' provide { true: '...', false: '...' }, for 'choice' provide { option1: '...', option2: '...' }, for 'score' provide an array of strings in order. | |
| question | Yes | The targeted question to evaluate (e.g., 'Will this change cause a breaking API error?'). |