Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

compare_silhouette_alignment

Compares a rendered 3D model silhouette against a reference image or cropped reference-sheet region at a chosen view, reporting pixel-level alignment metrics like IoU, Dice, and divergence.

Instructions

Compare a rendered 3D model silhouette against a reference image (or cropped reference-sheet region) from a specified orthographic or camera view (FRONT, SIDE, TOP, PERSPECTIVE). Produces measurable pixel-level alignment evidence: dimensions, foreground masks, intersection, union, IoU (Intersection-over-Union), Sørensen-Dice coefficient, and divergence score.

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": {
      "reference_image_path": "<reference_image_path>"
    },
    "name": "compare_silhouette_alignment"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoCapture pipeline: 'CAMERA' (default, rendered frames) or 'VIEWPORT' (interactive window). Headless requires CAMERA.CAMERA
viewNoCamera/orthographic viewpoint to capture and evaluate.FRONT
widthNoEvaluation image width in pixels.
heightNoEvaluation image height in pixels.
crop_boxNoOptional normalized crop bounds [u_min, v_min, u_max, v_max] in [0.0, 1.0] for reference sheet regions.
camera_nameNoOptional name of scene camera to use. If not specified, uses active scene camera.
mask_thresholdNoSensitivity threshold for foreground silhouette detection (0.0 to 1.0).
diff_output_pathNoOptional file path to save a color-coded visual difference mask (green=overlap, red=excess, blue=missed).
coordinate_systemNoCoordinate convention for crop_box: 'UV' (default, [0,0] bottom-left) or 'IMAGE_SPACE' ([0,0] top-left).UV
rendered_image_pathNoOptional filesystem path to a pre-rendered model image. When provided, skips in-engine render capture.
reference_image_pathYesFilesystem path to the reference image file.
reference_background_colorNoOptional background color [R, G, B, (A)] of the reference image. If omitted, sampled from image corner.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose the computed metrics (valuable since there is no output schema) and mentions that a color-coded diff mask can be written out, but it never states whether the operation has side effects beyond that optional file, what happens when the silhouette cannot be detected, or expected failure modes. Adequate but incomplete for a no-annotation 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?

Two sentences, front-loaded with the primary action and followed by the measurable outputs. Dense but no padding; slightly heavy metric enumeration, though it is genuinely informative given the absence of an output schema.

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

Completeness4/5

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

For a 12-parameter analysis tool with no output schema and no annotations, the description supplies the essential picture: what is compared, which views, and what the return payload contains. Remaining gaps (side effects beyond the diff file, error behavior, relationship to fit/optimize siblings) are real but secondary.

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 schema already documents all 12 parameters including enums, defaults, and ranges. The description adds only the view enum list and the crop-region concept, both already present in the schema, so the baseline 3 applies.

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 names a specific verb and resource: 'Compare a rendered 3D model silhouette against a reference image... from a specified orthographic or camera view,' and enumerates the concrete evidence produced (masks, intersection, union, IoU, Dice, divergence). This makes the measurement/evaluation role unmistakable, though it never states how it differs from the fitting/optimizing siblings.

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 only implied: the tool is clearly for evaluating alignment, and naming 'cropped reference-sheet region' hints at the reference-sheet workflow, but there is no explicit when-to-use or when-not-to-use guidance versus analyze/optimize siblings. An agent must infer that this is the diagnostic step rather than the corrective step.

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