# classify-seriousness

`station__calculate__classify-seriousness` · external (needs EXECUTION_BACKEND_URL configured) · domain `calculate` · pv-relevance `non-pv`

Classify adverse event seriousness per ICH E2A criteria. An event is serious if it meets ANY criterion: death, life-threatening, hospitalization, disability, congenital anomaly, or medically important.

> **Note:** This tool routes through an external execution backend. If `EXECUTION_BACKEND_URL` is unset on the server, calls return JSON-RPC error `-32603 "Tool execution backend not configured"`. Tools with `backend: native` execute in-process and are always callable.

## Agent metadata

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

## Input schema

- `resulted_in_death` *boolean* (required) — Did the event result in death?
- `life_threatening` *boolean* (required) — Was the event life-threatening at the time of occurrence?
- `required_hospitalization` *boolean* (required) — Did the event require or prolong hospitalization?
- `resulted_in_disability` *boolean* (required) — Did the event result in persistent or significant disability?
- `congenital_anomaly` *boolean* (required) — Did the event result in a congenital anomaly/birth defect?
- `medically_important` *boolean* (required) — Is the event medically important based on clinical judgment?

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__calculate__classify-seriousness",
    "arguments": {
      "resulted_in_death": false,
      "life_threatening": false,
      "required_hospitalization": false,
      "resulted_in_disability": false,
      "congenital_anomaly": false,
      "medically_important": false
    }
  }
}
```

## Related

- [/tools](/tools) — all 3062 tools
- [/tools/calculate__classify-seriousness](/tools/calculate__classify-seriousness) — HTML page
- [/tools/calculate__classify-seriousness/json](/tools/calculate__classify-seriousness/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide