decide
Score 1–64 typed questions about a state in one forward pass. Get calibrated probabilities per option without text generation or output parsing.
Instructions
Decision-model scoring (ollama /v1/systemone — clef / clef-flash / nimble / tev). Scores 1–64 TYPED questions about a state in ONE forward pass and returns calibrated probabilities per option — no text generation, no output parsing, no retries. Prefer over classify when a decision model is available: you get real probabilities instead of parsed JSON. Question types: 'choice' (criteria maps option keys→descriptions, null uses the key), 'score' (numeric scale), 'noul' (true/false). Requires an ollama provider running a decision model; a normal chat model returns an error. State is read server-side — files never enter your context.
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": {
"questions": "<questions>"
},
"name": "decide"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| glob | No | Glob for state files | |
| path | No | State from a file (read server-side) | |
| model | No | Decision model, e.g. 'clef-flash:9b' (default: provider default_model) | |
| paths | No | Multiple state files | |
| state | No | Inline state (plain text or JSON text) | |
| provider | No | ||
| questions | Yes | Named questions, 1–64 |