Skip to main content
Glama

viewport_screenshot

Capture the actual Blender GUI window as an inline image with an artifact path, including viewport overlays, selection, and editor UI for remote session inspection.

Instructions

Capture the actual Blender GUI window and return an inline image plus its artifact path.

Requires a GUI session. This includes viewport overlays, selection and editor UI.
It is separate from a Cycles camera render. If the job is still queued, poll its ID
and retrieve the resulting artifact with view_image.

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": {
      "session_id": "<session_id>"
    },
    "name": "viewport_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
session_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it discloses non-obvious traits: the capture includes viewport overlays, selection and editor UI, it requires a GUI session, and the operation may be asynchronous with a job ID to poll. It does not state whether the call blocks or whether the capture reflects the live session state at call time, 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core capability and its return value are front-loaded in the first sentence, with constraints and the queued-job path following in short, scannable sentences. There is minor fragmentation and stray whitespace but no filler content.

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?

With no output schema and no annotations, the description does the necessary work: it describes the returned inline image and artifact path, the GUI-session requirement, the UI elements included in the capture, and the polling fallback for queued jobs. Only the `session_id` sourcing and blocking/timeout behavior remain unstated.

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 coverage is 0%, so the single `session_id` parameter is undocumented in the schema, and the description only indirectly links it via "Requires a GUI session." It adds no guidance on which session to pass or how to obtain a valid GUI session ID (e.g. via `list_sessions`), leaving a real gap for a one-parameter tool.

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 gives a specific verb and resource ("Capture the actual Blender GUI window") plus the return shape ("inline image plus its artifact path"). It explicitly distinguishes itself from the Cycles camera render path, so an agent can separate it from the `render` sibling without opening either schema.

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 states a precondition ("Requires a GUI session") and rules out the common confusion with camera rendering by naming the separate render path. It also tells the agent what to do when the job is queued (poll the ID, then fetch with `view_image`). It does not explicitly say "use render instead when you want a camera render," but the contrast is clear enough to route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.