ocr_image
Extract text from local image files and receive recognized lines with optional per-line confidence scores and bounding-box coordinates.
Instructions
Recognize text in a local image file. Returns text + per-line confidence + coordinates.
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": {
"image_path": "<image_path>"
},
"name": "ocr_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image_path | Yes | ||
| return_polys | No | ||
| return_scores | No |