Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

scene_adapter_capture_2d

Paint the current 2D viewport once, then resolve its owned framebuffer to a PNG for visual verification of the scene.

Instructions

Paint the current 2D viewport once, then resolve its owned framebuffer to PNG.

No caller path, window restore, focus or event pump. Normal Qt/MD paint cache effects are allowed. Owned GL objects/context/bindings require cleanup; full GL purity and semantic scene content remain unproved. Root independently checks actual native preservation.

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>",
      "scene_token": "<scene_token>"
    },
    "name": "scene_adapter_capture_2d"
  }
}

Input Schema

NameRequiredDescriptionDefault
view_refYes
budget_msNo
scene_tokenYes
view_fingerprintYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior: single paint pass, framebuffer readback to PNG, no event pump or focus changes, paint cache effects permitted, and owned GL objects/context requiring cleanup. The trailing caveats about 'unproved' purity and an external 'Root' check are opaque, which keeps it short of a 5.

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 core operation is front-loaded in one efficient sentence, but the follow-on lines are fragmented and lean on unexplained jargon ('semantic scene content', 'Root independently checks') that costs space without adding usable meaning.

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?

For a four-parameter, three-required tool with no annotations, no output schema, and undocumented parameters, the description omits the return shape beyond 'PNG' and never defines the identifying inputs. What is present is honest about limitations but not sufficient to call the tool correctly.

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

Parameters1/5

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

All four parameters (view_ref, view_fingerprint, scene_token, budget_ms) have zero schema description coverage, and the description explains none of them. An agent learns nothing about what a scene_token or view_fingerprint must be, nor how budget_ms interacts with the single paint pass.

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 concrete verb and resource: paint the current 2D viewport once and resolve its owned framebuffer to PNG. That is distinguishable from scene_adapter_inspect_2d, though the description never names a sibling to make the boundary explicit.

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 statement of when this should be chosen over alternatives such as scene_adapter_inspect_2d or world_frame_capture. The phrasing 'No caller path, window restore, focus or event pump' describes what the tool does not do rather than when to invoke it, so selection guidance is largely absent.

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