# Microgram: local-seriousness-classify

`station__algovigilance__microgram-local-seriousness-classify` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Pre-filter: classify adverse event seriousness using local Ollama (qwen2.5:3b). Zero API cost. ~6s on CPU. ICH E2A criteria. Routes to local_nexvigilant_com_classify Station tool.

## Agent metadata

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

## Input schema

- `narrative` *string* (required) — Adverse event report narrative text

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-local-seriousness-classify",
    "arguments": {
      "narrative": ""
    }
  }
}
```

## Related

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