Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

optimize_mesh_silhouette

Iteratively deform a target mesh to match reference silhouettes from front, side, or top views, with bounded steps, topology preservation, and automatic rollback on failed improvement.

Instructions

Iteratively deform and optimize an explicitly designated target mesh against a reference image or cropped reference-sheet view (FRONT, SIDE, TOP) using measured silhouette comparison. Enforces bounded transformation/displacement steps, monotonic IoU improvement, topology preservation, and automatic transactional rollback on failure or non-improvement.

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>",
      "reference_image_path": "<reference_image_path>"
    },
    "name": "optimize_mesh_silhouette"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNoOrthographic camera viewpoint to optimize against: 'FRONT', 'SIDE', or 'TOP'.FRONT
depthNoOptional signed surface relief depth in meters for SURFACE_DETAIL mode.
viewsNoOptional list of 2 or 3 view configurations for simultaneous multi-view fitting.
radiusNoBrush radius in meters for sculpt anatomy delegation.
task_idNoOptional task or workflow identifier.
approvedNoDEPRECATED / UNTRUSTED: Client-supplied approval flags in tool arguments are not trusted as proof of human consent.
crop_boxNoOptional normalized crop bounds [u_min, v_min, u_max, v_max] in [0.0, 1.0] for reference sheet regions.
strengthNoBrush strength factor for sculpt anatomy delegation.
landmarksNoOptional list of semantic landmark definitions for landmark-guided optimization.
step_sizeNoOptimization step rate factor between 0.01 and 2.0.
toleranceNoMinimum IoU improvement required to accept an iteration step.
brush_typeNoOptional brush operation for sculpt anatomy refinement delegation.
resolutionNoEvaluation image render width and height in pixels.
camera_nameNoOptional scene camera name to use for projection.
feature_typeNoOptional anatomical surface detail feature type for SURFACE_DETAIL mode.
use_symmetryNoWhether to enforce bilateral symmetry across symmetry_axis during optimization.
feature_scaleNoOptional feature scale in meters for SURFACE_DETAIL mode.
symmetry_axisNoReflection plane axis for bilateral symmetry.X
target_objectYesName of the target mesh object in the Blender scene to optimize.
mask_thresholdNoSensitivity threshold for foreground silhouette detection (0.0 to 1.0).
max_face_countNoUpper face/polygon cap limit before rejecting refinement.
max_iterationsNoMaximum number of optimization iterations to run (clamped between 1 and 20).
refinement_modeNoOptional refinement mode flag.STANDARD
max_displacementNoMaximum allowed displacement cap in Blender units (meters) per iteration.
max_vertex_countNoUpper vertex cap limit before rejecting refinement.
subdivision_typeNoSubdivision algorithm to use when refining mesh.CATMULL_CLARK
coordinate_systemNoCoordinate system convention for crop_box: 'UV' ([0,0] bottom-left) or 'IMAGE_SPACE' ([0,0] top-left).UV
mask_vertex_groupNoOptional name of a vertex group on the mesh to restrict optimization.
optimization_modeNoDeformation mode: 'BOUNDED_SCALE_TRANSLATE' (centroid & bounding extents), 'VERTEX_DISPLACEMENT' (contour vertex deformation), or 'HYBRID' (both).BOUNDED_SCALE_TRANSLATE
preserve_topologyNoStrictly preserve mesh topology (vertex, edge, and face counts remain invariant).
preserve_landmarksNoOptional flag to preserve semantic landmarks during refinement or detailing.
subdivision_levelsNoOptional Catmull-Clark subdivision level for multiresolution refinement delegation (1 to 4).
rollback_on_failureNoIf true, automatically rollback mesh state if objective does not strictly improve or on error.
reference_image_pathYesFilesystem path to the reference image or reference sheet file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden and discloses bounded transformation/displacement steps, monotonic IoU improvement, topology preservation, and automatic transactional rollback on failure or non-improvement. It does not state in-place mutation semantics, permissions, or return values, but the core behavioral constraints are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with purpose and followed by behavioral guarantees. There is no filler; every clause adds selection or safety information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 34-parameter mutation tool with no annotations and no output schema, the description covers purpose and key safety behavior but omits when to choose it over similar silhouette tools and what it returns. Schema descriptions fill parameter details, but contextual gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description reinforces key concepts such as FRONT/SIDE/TOP views, reference images, bounded displacement, and topology preservation, but adds no parameter-level syntax or defaults beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'deform and optimize an explicitly designated target mesh' against a reference image or cropped reference-sheet view using silhouette comparison. It is clear but does not explicitly differentiate itself from similar siblings such as fit_multiview_silhouette or compare_silhouette_alignment.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides no explicit when-to-use or when-not-to-use guidance and names no alternatives. The description implies it is for silhouette-based mesh optimization, but selection between similar sibling tools is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools