policy_explain

Active

declared in 1.26.0

Explains WHY an agent action was blocked or flagged by AgentGuard. Provide the tool name and optional context to get a human-readable explanation of which policies matched, what risk level was assigned, and what the agent can do to proceed. Essential for transparent AI governance.

Parameters schema

{
  "type": "object",
  "required": [
    "tool_name"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Optional agent/client ID for context"
    },
    "tool_name": {
      "type": "string",
      "description": "The MCP tool that was blocked e.g. generate_report"
    },
    "action_context": {
      "type": "string",
      "description": "Optional description of what the agent was trying to do"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

FeedOracle Compliance Agent

https://github.com/feedoracle/feedoracle-managed-agents

1/7 registries

View full server →