# Microgram: ml-signal-threshold

`station__algovigilance__microgram-ml-signal-threshold` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Classifies ML model signal probability into actionable tiers: confirmed signal, probable signal, borderline, probable noise, confirmed noise

## Agent metadata

- `idempotent`: true
- `read_only`: true
- `expected_latency_ms`: unknown (not yet contract-tested)
- `cost_tokens_estimate`: unknown

## Input schema

- `signal_probability` *number* (required) — Input variable signal_probability
- `model_auc` *number* — Input variable model_auc
- `prr` *number* — Input variable prr

## Example call

```json
POST /api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-ml-signal-threshold",
    "arguments": {
      "signal_probability": 0
    }
  }
}
```

## Related

- [/tools](/tools) — all 7718 tools
- [/tools/algovigilance__microgram-ml-signal-threshold](/tools/algovigilance__microgram-ml-signal-threshold) — HTML page
- [/tools/algovigilance__microgram-ml-signal-threshold/json](/tools/algovigilance__microgram-ml-signal-threshold/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide