generate_image
Generate an original image with AI to accompany a post (#441). Describe the picture you want; the workspace's brand style guide is applied server-side, so do NOT restate colours or visual style. Takes 10-30 seconds. Costs one of the account's monthly image credits and returns the balance. Over MCP it returns an s3_key you pass to draft_post / save_draft / update_draft via the images field; over SMS/WhatsApp the picture comes back as an attachment. Either way it is saved to the user's media library. Use upload_image instead when the user already has a picture.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"prompt": "<prompt>"
},
"name": "generate_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | Shape: square (1:1), portrait (2:3), or landscape (3:2). Default square. | |
| style | No | Visual register (default: illustration). | |
| prompt | Yes | What the image should show. Describe the picture, not the post. | |
| workspace | No | Optional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that. |