Tool call

Decide whether an agent action should run, need approval or be refused.

An agent wants to take an action: send an email, move money, delete a file. Before the call runs, ask whether it should run, need a person's approval or be refused, given what the user asked for and your rules.

The request

json

{
  "model": "myles-g-31b",
  "state": {
    "rules": "The assistant may read and draft emails. Sending to anyone outside example.co.uk needs the user's approval. Never send attachments containing customer data outside the company.",
    "user_request": "Tidy up my inbox and reply to anything urgent.",
    "proposed_call": {
      "tool": "send_email",
      "to": "Accounts team, supplier-invoices.net (outside the company)",
      "subject": "Customer list as requested",
      "attachments": ["customers_q3.xlsx"]
    }
  },
  "questions": {
    "verdict": {
      "type": "choice",
      "instructions": "What should happen to the proposed tool call?",
      "criteria": {
        "run": "It does what the user asked and follows the rules",
        "ask": "It may be fine but the rules need the user's approval first",
        "refuse": "It breaks the rules or goes beyond what the user asked"
      }
    }
  }
}

Reading the answer

json

"verdict": {"type": "choice", "choice": "refuse", "confidence": 0.79,
            "probabilities": {"run": 0.01, "ask": 0.10, "refuse": 0.89}}

Run only when run is above a high threshold. An action that cannot be undone deserves a higher one.
Otherwise, if refuse is above its threshold, block the call and tell the agent why; in every other case, ask the user.

What to watch

Approvals people give after an ask: if almost all are approved, that kind of call can move to run with a rule change.
Keep the rules in the state, word for word, so a change to the rules is a change to the request, not to the model.

If your agent runs in an MCP client, it can ask this question itself through the MCP server, which marks every answer below your threshold for a person.