Box the cards on a screenshot
suggest_regionsBoxes the cards on a screenshot in the brand kit (an upload or a recording frame) with a vision model, crops each and saves them on the asset. Captured pages already have their cards boxed from the page itself. 2 credits, nothing when it finds no card whose words read at 20 px in a promo.
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": {
"brand_id": "<brand_id>",
"asset_id": "<asset_id>"
},
"name": "suggest_regions"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | A gateway vision model; the cheapest that passed the eval by default | |
| names | No | Cards to be sure of, by their heading | |
| asset_id | Yes | A screenshot in the brand kit (get_brand lists them): an upload or a recording frame | |
| brand_id | Yes | A brand kit from list_brands (id or name). Brings the colours, fonts, logo, website and default copy (headline, call to action, small print); use instead of brand. |