Create review
create_reviewReview one asset against a brand's active Brand Skill for the requested checks. Linked files are downloaded and uploads are copied when the review is created. Each account can have 20 reviews pending or processing at once. Returns the review_id and status immediately. Then call get_review with the returned review_id and wait: true.
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_session_id": "<brand_session_id>",
"assets": "<assets>",
"checks": "<checks>"
},
"name": "create_review"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| assets | Yes | Image to review. Supported formats: PNG, JPEG, WebP, GIF, and SVG. | |
| checks | Yes | Aspects of the asset to evaluate against the Brand Skill. Select the checks relevant to the requested review. | |
| context | No | Optional. What the asset is for, or what was asked for. | |
| llm_model | No | The model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Omit it or pass "unknown" if you are not certain; the tool runs the same either way. Recorded only for the server developer's analytics. | |
| references | No | Supporting images to compare against, such as a logo or product photo. | |
| idempotency_key | No | Optional key for safely retrying this request. Reuse it only with the same input. | |
| brand_session_id | Yes | Brand session ID from list_brands for the brand to review against. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | Current review status. | |
| review_id | Yes | Review ID. Pass it as review_id to get_review. | |
| message_for_assistant | No | Context, explanations, or actionable guidance for the calling assistant. Hosts may display it, but it is not copy that must be shown to the user verbatim. |