describe_image
Generate image descriptions using a vision model. Specify detail level or ask a targeted question to obtain specific visual information.
Instructions
用视觉模型描述图片内容,返回文字描述。
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": {
"image": "<image>"
},
"name": "describe_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | 本地图片绝对路径或 http(s) 图片 URL | |
| detail | No | 细节程度,默认 balanced | |
| question | No | 可选的针对性问题 |