> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.revvue.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.revvue.ai/_mcp/server.

# ToolGuardrail

GraphQL object

Reference: https://docs.revvue.ai/api-reference/jonna-ai-agent/types/objects/tool-guardrail

## Fields

- `toolName` — Tool this rule targets: the exact (namespaced) tool name ('reply_guest', 'booking__create_booking'), a wildcard suffix ('booking__*'), or '*' for every tool.
- `action` — allow = run autonomously; judge = LLM judge evaluates; require_approval = human must approve first; suggest = shown to a human as a draft they send themselves (reply_guest); deny = the tool is blocked (filtered from binding when the rule is static, rejected per-call when arg conditions apply).
- `conditions` — Conditions (AND'd). Empty list = the rule always matches this tool.
- `judgePrompt` — Optional judge rules override, used when action='judge' (or as the ALWAYS pre-check rules for require_approval). None falls back to the tool's built-in semantic_checks.
- `note` — Human-readable why — surfaced in audit events and in the blocked-call message.

## Definition

```graphql
type ToolGuardrail {
  toolName: String!
  action: String!
  conditions: [Condition!]!
  judgePrompt: String
  note: String!
}
```