analyze_image
Perform structured image analysis returning a description and visual primitives (box/point coordinates with labels). Optionally, provide a question to focus on specific details.
Instructions
结构化分析:返回 description + visual_primitives(box/point 坐标与标签)。
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": "analyze_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | ||
| format | No | primitives 字段风格,默认 generic | |
| question | No | 可选的关注点 |