capture
Takes a screenshot of only the Character Animator window and saves bounded OCR results into a new workspace directory for visual evidence without starting recording.
Instructions
Capture only the Character Animator window with bounded OCR into a new workspace directory.
Observed text/geometry are visual evidence, not native scene IDs. Never starts recording.
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": {
"directory": "<directory>"
},
"name": "capture"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| directory | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| native | Yes | ||
| sha256 | Yes | ||
| identity | Yes | ||
| launches_application | Yes |