Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

world_frame_capture

Capture the current background 3D viewport as a PNG bound to its camera and scene; optionally compare world OBJ exports after confirming simulation is off.

Instructions

Capture the current background 3D viewport and bind the PNG to its camera and scene.

Pass a pattern UUID to require it as the only selected piece. With include_mesh, verify simulation is off and compare two world OBJ exports.

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": {
      "scene_token": "<scene_token>",
      "request_id": "<request_id>"
    },
    "name": "world_frame_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
request_idYes
scene_tokenYes
include_meshNo
pattern_uuidNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations at all, the description carries the full disclosure burden. It does add real behavioral context: a PNG artifact is created and bound to camera and scene, pattern_uuid acts as a single-selection constraint, and include_mesh requires simulation to be off and performs two OBJ exports. It says nothing about permissions, failure modes, or what is returned, so it is helpful but incomplete.

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?

The action is front-loaded in the first sentence, and the second paragraph is dedicated to the two optional flags, which is a sensible structure. The mid-sentence line break is awkward and slightly obscures the split between the two conditions, but there is no filler text.

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

Completeness2/5

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

There are no annotations and no output schema, and the schema itself documents none of the four parameters. In that situation the description should explain scene_token, request_id, and what a caller receives back (image handle, artifact path, or bound reference), none of which it does. For a capture tool that mutates state by binding an artifact, that is a meaningful hole.

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 0%, so the description must compensate. It explains pattern_uuid as a 'must be the only selected piece' constraint and include_mesh as triggering a sim-off OBJ comparison, which is genuine added meaning. The two required parameters, scene_token and request_id, are never mentioned, leaving half the surface undocumented.

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 and resource: capture the current background 3D viewport and bind the resulting PNG to its camera and scene. That is specific enough to distinguish it from a plain 2D capture, but it never names a sibling or states explicitly how it differs from scene_adapter_capture_2d or the world_adapter_inspect_* family.

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?

The second paragraph gives conditional instructions: pass pattern_uuid to require it as the only selected piece, and use include_mesh when you need a simulation-off OBJ comparison. That implies when the optional flags matter, but there is no guidance on when to choose this tool over the sibling capture/inspect tools, and no stated preconditions for the required scene_token.

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