vision
Analyze local images and return descriptions. Accepts optional questions for targeted analysis.
Instructions
Analyze a local image file using a vision-capable model and return a text description. Use this whenever the user shares an image/screenshot. Pass the absolute file path.
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": {
"path": "<path>"
},
"name": "vision"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute path to the image file on disk. | |
| question | No | Optional. What to look for or ask about the image. Defaults to a full description. |