vision_classify_gesture
Classifies 21 hand landmarks into gesture types such as open palm, fist, pinch, and thumbs up, with confidence scores, pinch metrics, and finger extension states.
Instructions
Classifies 21 3D/2D hand landmarks (MediaPipe format) into gesture types (e.g. open_palm, fist, pointing_up, peace_sign, pinch, thumbs_up, rock_on, ok_sign) with confidence score, pinch metrics, and individual finger extension states.
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": {
"landmarks": "<landmarks>"
},
"name": "vision_classify_gesture"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| landmarks | Yes | Array of 21 3D/2D hand landmarks (dicts with x, y, z or nested coordinate arrays). | |
| handedness | No | Handedness label ('Right', 'Left', or 'Unknown'). | Right |
| confidence_threshold | No | Minimum confidence threshold (0.0 - 1.0). |