# should_delegate_to_agent

A other tool on the AgentVeil Protocol MCP server.

Agent View of the PolicyLayer registry record for `should_delegate_to_agent`. HTML page: https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/should-delegate-to-agent

## Facts

- Tool: `should_delegate_to_agent`
- Server: AgentVeil Protocol (`agentveil-protocol/agentveil-sdk`) — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk.md
- Homepage: https://github.com/agentveil-protocol/agentveil-sdk
- Risk category: Other (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "should_delegate_to_agent",
    "arguments": {}
  }
}
```

## Why should_delegate_to_agent is rated Low

The tool name implies it evaluates whether to delegate work to an agent, which sounds like a read/query operation returning a boolean or recommendation. However, with an empty description, it's unclear if it has side effects (e.g., logging the delegation decision via log_avp_interaction sibling tool behavior).

From the tool's own definition: "Tool name 'should_delegate_to_agent' with empty description. Name suggests a decision/recommendation function about delegation."

## Use case

AI agents call should_delegate_to_agent as a supporting operation in AgentVeil Protocol workflows.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches AgentVeil Protocol:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "should_delegate_to_agent": {
      "limits": [
        {
          "counter": "should_delegate_to_agent_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on AgentVeil Protocol (11)

- `check_avp_reputation` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/check-avp-reputation.md
- `check_reputation` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/check-reputation.md
- `check_trust` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/check-trust.md
- `get_agent_info` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/get-agent-info.md
- `get_attestations_received` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/get-attestations-received.md
- `get_audit_trail` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/get-audit-trail.md
- `get_protocol_stats` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/get-protocol-stats.md
- `search_agents` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/search-agents.md
- `search_avp_agents` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/search-avp-agents.md
- `verify_audit_chain` — Read — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/verify-audit-chain.md
- `log_avp_interaction` — Write — https://policylayer.com/tools/agentveil-protocol-agentveil-sdk/log-avp-interaction.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agentveil-protocol-agentveil-sdk · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/agentveil-protocol-agentveil-sdk