All tools
ToolRead

Get track record

get_track_record

Weigh the user's stated confidence against history: hit rate, Brier score, calibration buckets, and slices by inference level, source tier, and run mode.

When to use it

Weigh the user's stated confidence against history: hit rate, Brier score, calibration buckets, and slices by inference level, source tier, and run mode.

Typical workflow

Use company context first, then thesis, claims, reviews, and evidence gaps.

What it returns

A calibration summary, plain-language hints, and recent resolutions with their probabilities and outcomes.

Avoid using it when

Do not present a small sample as a verdict on the user's judgment; hints only appear when there are enough resolutions.

Advanced input contract

Agent hosts use this JSON Schema to validate the exact input shape.

View full registry notes

Summarize how this user's resolved hypotheses, catalysts, and decisions turned out: hit rate, Brier score, calibration buckets, slices by inference level, source tier, and run mode, plain-language hints, and recent resolutions. Use it to weigh stated confidence against history. Use when: Weigh the user's stated confidence against history: hit rate, Brier score, calibration buckets, and slices by inference level, source tier, and run mode. Avoid when: Do not present a small sample as a verdict on the user's judgment; hints only appear when there are enough resolutions.

View JSON Schema
{
  "type": "object",
  "properties": {
    "folderId": {
      "type": "string",
      "format": "uuid"
    },
    "ticker": {
      "type": "string",
      "minLength": 1,
      "maxLength": 12
    },
    "companyId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 200,
      "default": 25
    }
  },
  "additionalProperties": false
}

Useful next tools