Prediction Scorecard
review_predictionsScore past setups against actual outcomes to measure hit/miss and calibration. Flag likely regime change and recommend re-measuring signal statistics when realized win rate falls 10 points below predicted.
Instructions
Score past setups from top_setups against what actually happened: per-prediction hit/miss, cumulative realized win rate vs predicted win rate (calibration). If realized falls 10%p+ below predicted, it flags a likely regime change and recommends re-measuring the signal statistics. This is the feedback loop that keeps recommendations honest over time.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "review_predictions"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |