Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

bake_texture

Bakes materials, lighting, normals, roughness, or ambient occlusion into an image texture on a target mesh using Cycles, with optional PNG export to disk.

Instructions

Bake materials, lighting, normals, roughness, or ambient occlusion into an image texture for a target mesh object using Cycles rendering engine. Supports saving to disk.

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": {
      "object_name": "<object_name>"
    },
    "name": "bake_texture"
  }
}

Input Schema

NameRequiredDescriptionDefault
widthNoBake image width in pixels (64 to 8192).
heightNoBake image height in pixels (64 to 8192).
marginNoPixel margin around baked UV islands (0 to 64).
task_idNoOptional task or workflow identifier.
approvedNoDEPRECATED / UNTRUSTED: Client-supplied approval flags in tool arguments are not trusted as proof of human consent.
bake_typeNoType of bake pass to perform.COMBINED
image_nameNoTarget image datablock name. Created if not already existing.
object_nameYesName of the target mesh object with valid UV coordinates.
save_filepathNoOptional file path to write the baked PNG image to disk.
use_selected_to_activeNoWhether to bake from selected objects to the active object.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations provided, the description must carry the behavioral load, and it does disclose two useful traits: the Cycles dependency and that results can be written to disk. It omits important behavior for a mutating bake operation — whether an existing image datablock is overwritten, whether scene/render state is modified, how long or expensive the bake may be, and what happens when UVs are missing.

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 tight sentences: the core action and output first, then the optional persistence capability. No filler, no restatement of the name, nothing that fails to earn its place.

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 10-parameter, annotation-free, output-schema-free mutation tool, the description is minimal but not misleading — it covers what is baked and that results can be saved. It leaves gaps around overwrite behavior, render-engine prerequisites, error conditions, and the interaction booleans, which an agent would need for confident invocation.

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% (10 params, all documented, plus a bake_type enum), so the baseline is 3. The description adds only a loose mapping of 'supports saving to disk' to save_filepath and says nothing about the resolution defaults, margin, use_selected_to_active, or the semantics of the deprecated 'approved' flag beyond what the schema already states.

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 concrete verb (bake) plus the resources baked (materials, lighting, normals, roughness, AO) and the target (a mesh object's image texture via Cycles). An agent can tell what the tool produces. It does not, however, differentiate itself from near-identical siblings such as bake_object_texture, bake_materials, and bake_mesh_surface_map, which is the only thing keeping it off a 5.

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?

There is no when-to-use guidance, no prerequisites (e.g. Cycles must be the active render engine, the object needs valid UVs), and no mention of when to prefer or avoid it relative to the similarly named bake siblings. The only contextual hint is 'using Cycles rendering engine', which is a fact about the implementation, not routing guidance.

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