understand_image
Understand images via AI vision: get detailed descriptions of single images, point out similarities and differences between multiple images, and answer specific questions about visual content.
Instructions
使用智谱免费视觉模型 glm-4.6v-flash 理解一张或多张图片(本地文件路径或 http(s) 图片 URL)。单图自动详细描述;多图分别描述并指出异同。可附带具体问题 question(中文回答)。
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": {
"images": "<images>"
},
"name": "understand_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| images | Yes | ||
| question | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |