analyze_image
Analyzes local images or screenshots with a vision-capable LLM, returning detailed textual descriptions so text-only models can interpret visual content.
Instructions
Analyzes local images or screenshots using a vision-capable LLM and returns a detailed textual description.
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_path": "<image_path>"
},
"name": "analyze_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | kimi-k2.6:cloud | |
| prompt | No | Describe this image in detail for a coding context. | |
| image_path | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |