Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

canvas_views

Reads current 2D/3D Qt view state and scene-bound references—viewport size, DPR, transforms, scroll, scene token—without activating Marvelous Designer. Use it to inspect view context before scene operations.

Instructions

Read current MD 2D/3D Qt views and fresh scene-bound references; does not move or activate MD.

Returns view_ref, view_fingerprint, viewport logical size, DPR, transforms, scroll, checked tool actions and scene_token. Scene coordinates are Qt units; they are not model millimetres or world XYZ. Does not capture an image or certify hidden camera state.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "canvas_views"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNoall
budget_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: it enumerates the returned fields (view_ref, view_fingerprint, DPR, transforms, scroll, scene_token), declares the coordinate system is Qt units rather than model millimetres or world XYZ, and explicitly disclaims mutation and image capture. It does not discuss permissions, whether the call forces a viewport refresh, or the meaning of the time budget, so it is not fully exhaustive.

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 core action and its scope lead the description, followed by return fields and then caveats, which is a sensible front-loaded order. Nearly every clause earns its place; the closing sentence is slightly crowded with three separate disclaimers.

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?

Because there is no output schema, the inline return-field list is genuinely necessary and largely fills that gap. However, for a tool with two undocumented parameters and no annotations, leaving the 'view' selector and 'budget_ms' entirely unexplained leaves an agent without enough to choose arguments confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, so the description must compensate and it does not. Neither the 'view' enum (all/2d/3d) nor 'budget_ms' is mentioned at all; the reader gets no guidance on what a millisecond budget constrains or what happens if it is exhausted.

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 uses a precise verb+resource pair ('Read current MD 2D/3D Qt views and fresh scene-bound references') and immediately bounds the scope with 'does not move or activate MD', which distinguishes it from the gesture/runtime siblings in the canvas family without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear negative selection criteria — it does not move or activate MD, does not capture an image, and does not certify hidden camera state — which tells an agent when to pick something else (e.g. a gesture or screenshot tool). It stops short of naming a specific alternative tool for those cases.

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