# Microgram: noncompensatory-score-dual

`station__algovigilance__microgram-noncompensatory-score-dual` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Compare additive (legacy) and geometric (non-compensatory) risk scores side-by-side. Detects compensatory masking where one strong metric inflates the additive score while geometric correctly identifies imbalanced evidence. Divergence > 1 level = masking detected.

## Agent metadata

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

## Input schema

- `drug` *string* (required) — Drug name
- `event` *string* (required) — Adverse event
- `prr` *number* (required) — Proportional Reporting Ratio
- `ror_lower` *number* (required) — ROR lower 95% confidence interval
- `ic025` *number* (required) — Information Component 2.5th percentile
- `eb05` *number* (required) — EBGM 5th percentile
- `n` *number* (required) — Number of cases

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-noncompensatory-score-dual",
    "arguments": {
      "drug": "",
      "event": "",
      "prr": 0,
      "ror_lower": 0,
      "ic025": 0,
      "eb05": 0,
      "n": 0
    }
  }
}
```

## Related

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