Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

crop_reference_image

Crop a rectangular region from a reference sheet image using normalized coordinates, save the result, and optionally load it into Blender as a calibrated reference object aligned to a chosen view.

Instructions

Crop a rectangular region from a reference sheet image using normalized [u_min, v_min, u_max, v_max] coordinates, save the cropped image, and optionally load it as a calibrated Blender reference object (Image Empty or Plane) with orthographic view alignment (FRONT, SIDE, TOP, USER).

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": {
      "image_path": "<image_path>",
      "crop_box": "<crop_box>"
    },
    "name": "crop_reference_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoName for the created Blender reference object.Reference_Crop
sizeNoPrimary dimension (meters) of the empty display size or plane dimension.
depthNoDisplay depth relative to geometry: 'DEFAULT', 'FRONT', or 'BACK'.DEFAULT
scaleNoScale factors [sx, sy, sz].
opacityNoDisplay transparency/alpha (0.0 = transparent, 1.0 = opaque).
crop_boxYesNormalized bounding box [u_min, v_min, u_max, v_max] in [0.0, 1.0] range, where u_min < u_max and v_min < v_max.
locationNo3D spatial position [x, y, z] in Blender units (meters).
view_axisNoOrthographic view alignment: 'FRONT' (facing -Y), 'SIDE' (facing +X), 'TOP' (facing +Z), or 'USER' (custom rotation).FRONT
image_pathYesFilesystem path to the source reference image (.png, .jpg, .jpeg, .webp, .tga, .bmp, .tif, .tiff, .exr).
output_pathNoDestination file path for the cropped image. Must not overwrite source image.
display_modeNoDisplay representation: 'EMPTY' (Blender Image Empty) or 'PLANE' (calibrated textured mesh plane).EMPTY
rotation_eulerNoExplicit Euler rotation [rx, ry, rz] in radians. Overrides view_axis default when provided.
coordinate_systemNoCoordinate convention: 'UV' (default, [0,0] bottom-left to [1,1] top-right) or 'IMAGE_SPACE' ([0,0] top-left to [1,1] bottom-right).UV
load_as_referenceNoIf true, load the cropped image into Blender as a reference object.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden. It does disclose the real behavior worth knowing — the crop is written to disk and may additionally create a Blender object with orthographic alignment — but it says nothing about side effects on existing objects, whether repeated calls create duplicate references, permission or write-failure behavior, or what happens when load_as_reference is false. Useful, but incomplete for a 14-parameter 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?

It is a single well-formed sentence that front-loads the primary action and then appends the optional outcomes in logical order. The enumeration of FRONT/SIDE/TOP/USER merely repeats the enum already visible in the schema, which is the one piece of waste.

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 tool with 14 parameters, no annotations, and no output schema, the description conveys the overall workflow but omits the return value (output file path? created object name?) and the interaction between output_path, load_as_reference, and existing scene objects. An agent could call it, but would be guessing about results.

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 every parameter including coordinate_system, view_axis, and rotation_euler override semantics. The description adds only a restatement of the normalized [u_min, v_min, u_max, v_max] convention and the four view axes, which duplicates schema content rather than extending it.

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

Purpose5/5

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

The description opens with a specific verb+resource pair ('Crop a rectangular region from a reference sheet image'), then enumerates the two secondary effects (saving the crop, optionally loading it as a Blender reference object). That is enough to separate it from siblings like load_reference_image (no cropping) and crop_vse_strip (VSE strips, not reference sheets).

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 context is implied rather than stated: 'optionally load it as a calibrated Blender reference object' hints that image-only cropping is a valid mode, controlled by load_as_reference. There is no explicit when-to-use guidance, no exclusion of alternatives such as load_reference_image, and no stated precondition that a reference sheet must already exist.

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