Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

scene_adapter_bezier_drag

Drag Bézier curve points in the active Edit Curve Point viewport with a fixed 2D hover/press plus Alt move/release batch, returning a structured result for the operation.

Instructions

One fixed 2D NoMod hover/press, Alt move/release batch in current Edit Curve Point mode.

This is a viewport primitive: native handle ownership, mm targets and preservation must be established independently. No arbitrary modifiers/events, OS input, focus or project changes.

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_ref": "<view_ref>",
      "view_fingerprint": "<view_fingerprint>",
      "start": "<start>",
      "end": "<end>",
      "scene_token": "<scene_token>",
      "request_id": "<request_id>"
    },
    "name": "scene_adapter_bezier_drag"
  }
}

Input Schema

NameRequiredDescriptionDefault
endYes
startYes
view_refYes
budget_msNo
request_idYes
scene_tokenYes
view_fingerprintYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden, and it does disclose real behavior: the exact modifier pattern is fixed, out-of-scope inputs (arbitrary modifiers, OS input, focus, project changes) are excluded, and it warns that native handle ownership, mm targets and preservation are not handled here and must be established independently. Still absent is anything about mutation semantics — whether the curve is actually modified, whether it is undoable, and how request_id or budget_ms affect idempotency and timeout behavior.

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?

The definition is short and front-loads the operation before the constraints, which is the right structure. But the two sentences are packed with unexplained internal vocabulary and trailing whitespace, so brevity comes at the cost of parseability rather than earning it.

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?

This is a high-complexity gesture primitive with 7 undocumented parameters, no annotations and no output schema, so the description must do the heavy lifting. It covers scope exclusions but leaves the agent without any understanding of parameter meaning, return behavior, failure modes, or whether the operation mutates the document — significant gaps for a call this complex.

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% across 7 parameters, 6 of them required, so the description needs to compensate and does not. Terms like 'mm targets', 'view_ref', 'scene_token', 'view_fingerprint' and 'budget_ms' map only obliquely, if at all, to named parameters, and start/end, request_id and the default 750ms budget are never explained in the description text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete action set — a single 2D hover/press with NoMod plus Alt move/release, applied in Edit Curve Point mode — so the resource and operation are identifiable. However, it is written in dense internal jargon ('NoMod', 'batch') and never contrasts itself with the very similar sibling scene_adapter_bezier_drag_unsnapped, so an agent cannot tell from the text alone why it would pick this tool over that one.

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 phrase 'One fixed ... batch' implicitly scopes each call to exactly one gesture sequence, and 'No arbitrary modifiers/events, OS input, focus or project changes' functions as a when-not boundary. What is missing is any explicit routing: no statement of when to choose this versus the unsnapped or world_adapter_gizmo_drag alternatives, and no stated preconditions or ordering relative to scene setup calls.

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