# hitl-submit

`station__agent-intel__hitl-submit` · external (needs EXECUTION_BACKEND_URL configured) · domain `agent-intel` · pv-relevance `non-pv`

by risk level and score. Each entry has an expiration (default 72 hours).

> **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

- `assign_to` *string*
- `evidence` *any*
- `expires_hours` *integer*
- `recommendation` *string* (required) — Recommended action (e.g., "investigate", "restrict_access", "emergency_withdrawal")
- `risk_level` *string* (required) — Risk level: "low", "medium", "high", "critical"
- `risk_score` *number* (required) — Risk score (0.0 - 10.0)
- `target` *string* (required) — Target entity (e.g., drug name, signal ID)
- `tool` *string* (required) — Source tool that generated the decision (e.g., "guardian_evaluate_pv")

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__agent-intel__hitl-submit",
    "arguments": {
      "recommendation": "",
      "risk_level": "",
      "risk_score": 0,
      "target": "",
      "tool": ""
    }
  }
}
```

## Related

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