detect_semantic_landmarks
Detect semantic anatomical landmarks like snout, horn, wing, and tail points from calibrated silhouettes or mesh curvature, project them to surface vertices, and optionally save them on the mesh.
Instructions
Automatically detect semantic anatomical landmarks (snout, horn apices, wing apices, tail tip) from calibrated reference silhouettes or mesh boundary curvature, project to closest surface vertices, and optionally persist them into the target mesh datablock.
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": {
"target_object": "<target_object>"
},
"name": "detect_semantic_landmarks"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| views | No | Optional list of calibrated reference views for 2D silhouette contour extrema detection. | |
| task_id | No | Optional task or workflow identifier. | |
| approved | No | DEPRECATED / UNTRUSTED: Client-supplied approval flags in tool arguments are not trusted. | |
| object_name | No | Alias for target_object. | |
| store_on_mesh | No | Whether to store the detected landmarks in target object's custom properties (_umcp_semantic_landmarks). | |
| target_object | Yes | Name of the target mesh object in the Blender scene. | |
| landmark_types | No | List of anatomical landmark types to detect. Defaults to standard dragon features. | |
| detection_method | No | Algorithm for feature detection: 'CONTOUR_EXTREMA' from silhouette, 'BOUNDING_PROJECTION' from view-aligned bounds, or 'CURVATURE_PEAKS' from mesh geometry. | CONTOUR_EXTREMA |
| enforce_symmetry | No | Enforce bilateral symmetry across sagittal X axis for paired landmarks (horn, wing, claws). | |
| max_vertex_distance | No | Maximum 3D distance allowed when projecting landmark rays onto target mesh vertices. | |
| confidence_threshold | No | Minimum confidence threshold to include a detected landmark. |