recommend_combinations
Suggests ranked multi-layer algorithm combinations for a given artistic intent, returning recipes with layers, moods, and descriptions to plan generative artworks.
Instructions
Suggest multi-layer algorithm combinations for a given artistic intent.
Returns a dict with:
- intent (str): the original intent string
- combinations (list): ranked list of layered recipes
- tip (str): guidance for following up on returned paths
Each combination includes:
- name (str): recipe name
- description (str): recipe description
- moods (list[str]): associated creative moods
- layers (list): each layer has role (str), query (str), and suggestions
(list of manifest entries resolved by search_algorithms)
Layer roles describe compositional function (e.g. background, agents, texture,
overlay). Suggestions are live manifest entries — use get_algorithm_summary or
get_algorithm on any suggested path for full details.
Use this tool to plan layered generative artworks from a text description.
It combines curated recipes with dynamic algorithm lookup per layer.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| intent | Yes | Free-text description of the artistic intent or visual goal (e.g. 'cosmic void with particle trails', 'organic growth with geometric structure', 'flowing smoke with invisible force fields'). Used to rank curated multi-layer recipes by keyword relevance. | |
| count | No | Number of combination recipes to return. Accepts integers in the range 1 to the total number of available recipes. Default: 3. Recipes are ranked by how closely their name, description, moods, and layer queries match the intent. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||