# Microgram: vigilance-harm-classify

`station__algovigilance__microgram-vigilance-harm-classify` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Classify an adverse drug reaction into a harm type (A-H) from three binary attributes per Theory of Vigilance §9. Example: single + acute + deterministic = Type A (Augmented, dose-dependent). Use to select monitoring strategy appropriate for the harm mechanism.

## Agent metadata

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

## Input schema

- `determinism` *string* (required) — Response determinism: "deterministic" or "stochastic".
- `multiplicity` *string* (required) — Perturbation multiplicity: "single" or "multiple".
- `temporal` *string* (required) — Temporal profile: "acute", "chronic", or "any".

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-vigilance-harm-classify",
    "arguments": {
      "determinism": "",
      "multiplicity": "",
      "temporal": ""
    }
  }
}
```

## Related

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