Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

refine_mesh_multiresolution

Refines a target mesh with bounded multiresolution subdivision and aligns its silhouettes to calibrated FRONT, SIDE, or TOP reference views, rolling back changes when alignment fails to improve.

Instructions

Perform bounded multiresolution surface refinement and contour alignment on an explicitly designated target mesh against one or more calibrated reference views (FRONT, SIDE, TOP). Applies controlled subdivision with strict vertex, face, displacement, and iteration bounds, evaluates multi-view silhouette alignment with regression protection, and enforces transactional rollback if objective fails to improve or limits are violated.

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": "refine_mesh_multiresolution"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNoOrthographic view if single reference image is specified: 'FRONT', 'SIDE', or 'TOP'.FRONT
viewsNoList of 1 to 3 distinct orthographic reference view configurations (FRONT, SIDE, TOP).
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].
objectiveNoMulti-view aggregate objective function to maximize.WEIGHTED_IOU
step_sizeNoRefinement step rate factor between 0.01 and 1.0.
toleranceNoMinimum aggregate objective improvement required to accept an iteration step.
resolutionNoEvaluation image render width and height in pixels.
camera_nameNoOptional scene camera name to use for evaluation.
use_symmetryNoWhether to enforce bilateral symmetry across symmetry_axis during sculpting.
symmetry_axisNoReflection plane axis for bilateral symmetry (default 'X' for sagittal symmetry).X
target_objectYesName of the target mesh object in the Blender scene to refine.
mask_thresholdNoSensitivity threshold for foreground silhouette detection.
max_face_countNoMaximum allowed face/polygon count limit; pre-modification check rejects if exceeded.
max_iterationsNoMaximum number of surface refinement iterations.
seam_thresholdNoMidline distance threshold in meters. Midline vertices within this distance to symmetry plane are clamped to zero displacement along the symmetry axis.
max_displacementNoMaximum allowed displacement cap in Blender units (meters) per iteration.
max_vertex_countNoMaximum allowed vertex count limit; pre-modification check rejects if exceeded.
subdivision_typeNoSubdivision algorithm: 'CATMULL_CLARK' (smooth surface) or 'SIMPLE' (linear subdivision).CATMULL_CLARK
coordinate_systemNoCoordinate system convention: 'UV' or 'IMAGE_SPACE'.UV
mask_vertex_groupNoOptional name of a vertex group on the mesh to restrict and modulate sculpt stroke displacement weights [0.0..1.0].
subdivision_levelsNoNumber of subdivision levels to apply (clamped between 1 and 4).
rollback_on_failureNoIf true, automatically rollback mesh state if objective does not strictly improve or regression tolerance is violated.
reference_image_pathNoOptional single reference image path if 'views' is omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses controlled subdivision with vertex/face/displacement/iteration bounds, multi-view silhouette evaluation with regression protection, and transactional rollback when the objective fails to improve. It omits what the mesh looks like after a successful run (topology changed in place?) and whether a result report is returned, which is a real gap for a mutating tool.

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

Conciseness4/5

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

A single dense sentence cluster with purpose front-loaded and each clause carrying distinct information (bounds, evaluation, rollback). It is long but not padded; only the redundant restatement of 'bounded' and 'strict... bounds' could be trimmed.

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 25-parameter mutating tool with no annotations and no output schema, the description covers the core mechanics and failure handling well. It leaves out return behavior, approval requirements (the deprecated 'approved' flag is only explained in the schema), and any guidance on typical reference-view setup, so an agent still faces open questions before invoking it.

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 every one of the 25 parameters is already documented in the schema; baseline 3 applies. The description adds only category-level meaning ('strict vertex, face, displacement, and iteration bounds') rather than clarifying specific parameter interactions, such as how tolerance, max_regression_tolerance, and rollback_on_failure combine.

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?

The description states a specific verb pair ('perform bounded multiresolution surface refinement and contour alignment') on a named resource ('explicitly designated target mesh') with reference inputs ('calibrated reference views'). It is clearly distinguishable from generic mesh siblings such as bevel_mesh or sculpt_mesh, but it never names an alternative tool, so routing still requires inference.

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

Usage Guidelines3/5

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

Usage is implied: you need a target mesh plus one or more calibrated orthographic reference views, which hints at a prior calibrate_reference_views step without saying so. There is no explicit when-to-use/when-not-to-use statement and no comparison against related tools like optimize_mesh_silhouette or sculpt_mesh.

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