Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

inspect_scene_data

Inspect structured Blender scene data read-only through an explicit category allowlist to retrieve scene summaries, object details, topology, materials, and render settings safely.

Instructions

Inspect structured Blender scene data with an explicit, safe read-only allowlist. Supported categories: 'scene_summary', 'object_modifiers', 'object_materials', 'mesh_topology', 'scene_hierarchy', 'world_settings', 'collection_tree', 'render_settings', 'blender_info', 'uv_layers', 'render_result', 'cameras', 'camera_settings'. Arbitrary code execution and unapproved data access are strictly rejected.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum items for collection/hierarchy or indexed mesh queries.
offsetNoPagination offset for collection/hierarchy or indexed mesh queries.
categoryYesCategory of scene data to inspect.
mesh_sourceNoIndexed topology only. Base is editable source; evaluated is a temporary modifier result, freed after readback. Object Mode only; evaluated indices cannot authorize base-mesh edits.
target_nameNoTarget object name in the active scene. Required for object-specific categories ('object_modifiers', 'object_materials', 'mesh_topology', 'uv_layers').
element_domainNoOptional indexed base-mesh domain for mesh_topology only. Object Mode, active-scene mesh only. Omitting preserves count-only response. Local coordinates; indices are snapshot-local. Paginated with limit/offset; oversized snapshots/pages fail explicitly.
include_parametersNoWhether to include detailed property values for modifiers/materials.
expected_snapshot_idNoIndexed topology only: reject the page if geometry/source changed since this fingerprint.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations supplied, the description does useful work by declaring the tool read-only and allowlist-based, and by stating that unapproved access is rejected — genuine behavioral context beyond the schema. However it omits the snapshot/consistency protocol implied by expected_snapshot_id, does not say what happens to oversized snapshots, and does not describe the response shape (there is no output schema to compensate).

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

Conciseness3/5

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

Two sentences, front-loaded with the purpose, which is good structure. But roughly half the text is a comma-separated category enumeration that duplicates the schema enum while omitting 'compositor_pipeline' and 'compositor_settings', so the bulk of the description is redundant and slightly inaccurate rather than informative.

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?

The input schema is fully annotated, which carries much of the load for an eight-parameter tool with allOf conditionals. Still, the description never surfaces the conditional requirements (mesh_topology forcing target_name/element_domain, offset>0 forcing expected_snapshot_id), and its category list contradicts the actual enum by leaving out the two compositor categories, which could lead an agent to believe compositor data is unavailable through this tool.

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% and the eight parameters are already richly documented in the schema, including mesh_source semantics, element_domain indexing, and the expected_snapshot_id fingerprint pattern, so the baseline of 3 applies. The description adds no meaning beyond a category list that duplicates — and in fact undercounts — the enum.

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 ('Inspect structured Blender scene data') and backs it with an enumerated allowlist of categories, so the agent knows exactly what data it can retrieve. It falls short of a 5 because it never distinguishes itself from overlapping siblings such as inspect_compositor_pipeline, inspect_uv_mesh, or inspect_material_shader, leaving the agent to guess which entry point to use.

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 or when-not-to-use guidance relative to alternatives; the category list merely restates the enum already present in the schema. The only constraint offered ('Arbitrary code execution and unapproved data access are strictly rejected') is a safety boundary, not selection guidance, and the many overlapping inspect_* siblings are never addressed.

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