# run-pun-proof-detector

`station__microgram__run-pun-proof-detector` · external (needs EXECUTION_BACKEND_URL configured) · domain `microgram` · 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.

> **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

- `author_domain` *string* (required) — Input parameter: author_domain
- `reader_domain` *string* (required) — Input parameter: reader_domain
- `term` *string* (required) — Input parameter: term

## Example call

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

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

## Related

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