Prepare Image Picker Uploads
create_image_picker_uploadsPrepare temporary uploads for the Brand Library image picker opened by open_upload_ui. Supply that Brand's brand_session_id and the selected files' filenames, byte lengths, and MIME types when known. Returns an upload_id and PUT instructions for each file. The picker must upload the bytes and call upload_image to finish saving each image.
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>",
"files": "<files>"
},
"name": "create_image_picker_uploads"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | Yes | Local files to stage, described by their filenames, exact byte lengths, and MIME types when known. Their combined size must not exceed 256 MiB. | |
| 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. | |
| brand_session_id | Yes | Brand session ID that open_upload_ui opened the picker for. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| uploads | Yes | One upload reservation for each requested file. | |
| 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. |