capture_screen_and_extract_text
Capture screenshots and extract text using OCR in one step. Supports full screen or specific application windows with multi-language text recognition.
Instructions
Captures a screenshot and extracts text from it in one operation. Can capture full screen or a specific application window.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| display | No | Display number (0 for primary display) - ignored if applicationName is provided | |
| language | No | Language code for OCR (e.g., eng, spa, fra) | eng |
| applicationName | No | Name of the application to capture (e.g., 'Safari', 'Chrome'). If provided, captures only this application's window instead of full screen. |