# Microgram: pun-proof-detector

`station__algovigilance__microgram-pun-proof-detector` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Perspective divergence detector: flags terms where author and reader hold different boundaries for the same word. Routes to BLOCK (risk >= 2.5), ESCALATE (>= 1.5), or FLAG (< 1.5). Chains upstream of signal-detect.

## Agent metadata

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

## Input schema

- `term` *string* (required) — The term to check for perspective divergence (e.g., expected, safe, related)
- `author_domain` *string* (required) — Domain perspective of the author (e.g., Clinical, Regulatory, Patient, Statistics)
- `reader_domain` *string* (required) — Domain perspective of the reader (e.g., PV, Regulatory, Post-market, Signal)

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-pun-proof-detector",
    "arguments": {
      "term": "",
      "author_domain": "",
      "reader_domain": ""
    }
  }
}
```

## Related

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