Describe Image
describe_imageAnalyze images using a vision model to answer questions or generate descriptions. Supports local files, URLs, base64, and multiple image inputs.
Instructions
Analyze one or more images with an OpenAI-compatible vision model. Supports local image_path, image_url, image_base64, or ordered images[].
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "describe_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| images | No | Ordered list of images to analyze. Use this for multiple images; do not combine it with top-level image fields. | |
| prompt | No | Specific question or instruction about the image(s). Leave empty for a full description. | |
| image_url | No | Public http(s) URL of an image that the configured vision model provider can access. | |
| image_path | No | Absolute path to a local raster image file. Use this when the image is available on disk. | |
| image_base64 | No | Base64-encoded image data without a data: URI prefix. | |
| image_mime_type | No | MIME type for image_base64. If omitted, VisionPro detects it from image bytes. |