ocr
Extract text from a screenshot of a target app using a local OCR backend. Returns normalized confidence, pixel boxes, and a short-lived ID for automation.
Instructions
Run a local OCR backend on a newly captured, privacy-filtered target screenshot. Returns normalized confidence 0..1, screenshot pixel boxes, and an opaque short-lived ocr_id.
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": {
"app": "<app>"
},
"name": "ocr"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| app | Yes | App name, Hyprland class/title, pid, or address:0x... selector. | |
| region | No | ||
| backend | No | auto | |
| timeout | No | Local OCR timeout. | |
| language | No | ||
| coordinate_space | No | Coordinate space. screenshot uses get_app_state pixels; window uses logical coordinates from the target window's top-left. | screenshot |
| page_segmentation_mode | No |