Find recipes using natural language search. Use this tool when:
- User refers to a recipe by partial name, description, or keywords (e.g., "run my GitHub PR recipe", "the slack notification one")
- User wants to find a recipe but doesn't know the exact name or ID
- You need to find a recipe_id before executing it with RUBE_EXECUTE_RECIPE
The tool uses semantic matching to find the most relevant recipes based on the user's query.
Input:
- query (required): Natural language search query (e.g., "GitHub PRs to Slack", "daily email summary")
- limit (optional, default: 5): Maximum number of recipes to return (1-20)
- include_details (optional, default: false): Include full details like description, toolkits, tools, and default params
Output:
- successful: Whether the search completed successfully
- recipes: Array of matching recipes sorted by relevance score, each containing:
- recipe_id: Use this with RUBE_EXECUTE_RECIPE
- name: Recipe name
- description: What the recipe does
- relevance_score: 0-100 match score
- match_reason: Why this recipe matched
- toolkits: Apps used (e.g., github, slack)
- recipe_url: Link to view/edit
- default_params: Default input parameters
- total_recipes_searched: How many recipes were searched
- query_interpretation: How the search query was understood
- error: Error message if search failed
Example flow:
User: "Run my recipe that sends GitHub PRs to Slack"
1. Call RUBE_FIND_RECIPE with query: "GitHub PRs to Slack"
2. Get matching recipe with recipe_id
3. Call RUBE_EXECUTE_RECIPE with that recipe_id