Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

canvas_gesture

Sends one validated left-button click or drag to a current 2D/3D Marvelous Designer viewport using logical pixel points, enabling AI clients to interact without window activation.

Instructions

Send ONE complete left-button click/drag to a freshly read current 2D/3D view.

Points are viewport LOGICAL pixels, independent of DPR: click=[start]; drag=[start, intermediate...,end], at most 32 points. Uses the current tool without selecting modes. Modifiers affect these synthetic events only. MD must already be inactive/background; no window restore, activation or OS input is used. Native preflight validates dynamic bounds, references and mappings before any events. Release/cleanup is in this same RPC.

SUCCEEDED proves the closed event batch and public view readback only; selection hits, geometry, handles and XYZ require separate domain readback. Partial/unknown dispatches need root recovery; do not retry with a new request_id. Budget is cooperative between events, not a native callback timeout. Requires the scene_token returned by canvas_views.

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": {
      "view": "<view>",
      "view_ref": "<view_ref>",
      "view_fingerprint": "<view_fingerprint>",
      "action": "<action>",
      "points": "<points>",
      "scene_token": "<scene_token>",
      "request_id": "<request_id>"
    },
    "name": "canvas_gesture"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewYes
actionYes
pointsYes
view_refYes
budget_msNo
modifiersNo
request_idYes
scene_tokenYes
view_fingerprintYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations the description carries the full load, and it does: native preflight validation before any events, release/cleanup in the same RPC, what SUCCEEDED actually proves (closed batch plus public readback, not selection hits/geometry handles/XYZ), root recovery required for partial dispatches, and that budget is cooperative between events rather than a native timeout.

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?

Front-loaded with the core action and dense but purposeful; nearly every sentence adds a constraint an agent could not infer. Some phrasing is telegraphic ('Partial/unknown dispatches need root recovery') but remains interpretable.

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

Completeness4/5

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

For a nine-parameter, no-annotation, no-output-schema tool, this covers preconditions, validation, failure semantics, and recovery. The remaining gap is that the provenance of view_ref and view_fingerprint, and the full success payload shape, are only implied.

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

Parameters4/5

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

Schema description coverage is 0% across nine parameters, so the description must compensate, and it largely does: points are viewport LOGICAL pixels independent of DPR, click=[start] vs drag=[start, intermediate..., end] with a 32-point cap, modifiers apply to synthetic events only, scene_token is sourced from canvas_views, and budget is cooperative. view_ref and view_fingerprint are left unexplained, keeping it below a 5.

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 opening sentence names a specific verb and resource: send ONE complete left-button click/drag to the current 2D/3D view. That is precise about scope and payload shape. It does not name a sibling to differentiate against, so it stops short of 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 Guidelines4/5

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

It gives concrete preconditions (MD must already be inactive/background, scene_token must come from canvas_views, no window restore/activation) and anti-patterns (do not retry with a new request_id). It lacks an explicit when-to-use-this-vs-another-tool statement, but the operating context is clear.

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