left_click
Perform a grounded left click in the latest capture’s pixel space, using OCR-center or visual coordinates, and report which grounding route was used.
Instructions
Last-resort grounded left click in the most recent capture's pixel space. Pass source=ocr_center when x/y came from focused OCR; otherwise source=visual_coordinate (the default) means a focused screenshot/zoom. The result reports that route.
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": {
"x": "<x>",
"y": "<y>"
},
"name": "left_click"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| x | Yes | ||
| y | Yes | ||
| source | No | Grounding source for route reporting. Use `ocr_center` only for a center returned by the immediately preceding OCR result. Omit/default `visual_coordinate` for a focused screenshot/zoom coordinate. | |
| background | No | Deliver in the background to the captured window's process (native apps only; browsers/Electron ignore it). Default false = foreground. |