# classify

`station__harm-taxonomy__classify` · external (needs EXECUTION_BACKEND_URL configured) · domain `harm-taxonomy` · pv-relevance `pv-core`

Classify a harm event by three binary attributes: multiplicity (single/multiple), temporal profile (acute/chronic), and response determinism (deterministic/stochastic). Returns best-matching harm type (A-H) with confidence, conservation laws violated, and manifestation levels.

> **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

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

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__harm-taxonomy__classify",
    "arguments": {
      "multiplicity": "",
      "temporal": "",
      "determinism": ""
    }
  }
}
```

## Related

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