Skip to main content
Glama
HoldMyBeer-gg

blend-ai

by HoldMyBeer-gg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_viewport_screenshot

Capture the current Blender 3D viewport as a PNG screenshot, choosing fast OpenGL mode or a full render, with an optional max pixel size.

Instructions

Capture a screenshot of the current Blender 3D viewport.

Args: max_size: Maximum size in pixels for the largest dimension (default: 1000). mode: Capture mode - 'fast' for instant viewport capture using OpenGL (default), 'full' for a complete render through the active render engine.

Returns: Dict with base64-encoded PNG image data, width, height, format, and mode.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNofast
max_sizeNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.7.0
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / mode / enum
      Added value: +[
+  "fast",
+  "full"
+]
  2. Changed3 schema fields changedv1.2.2
    • addedInput schema / properties / mode
      Added value: +{
+  "default": "fast",
+  "title": "Mode",
+  "type": "string"
+}
    • removedInput schema / properties / user_prompt
      Removed value: -{
-  "default": "",
-  "title": "User Prompt",
-  "type": "string"
-}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "get_viewport_screenshotDictOutput",
+  "type": "object"
+}
  3. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full disclosure burden. It usefully describes the return payload (base64 PNG plus width, height, format, mode) and the tradeoff between the two capture modes, but never states that the operation is non-mutating, whether it works in background/headless contexts, or any cost/latency implications of 'full' mode.

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 a one-line purpose, then structured Args/Returns blocks. Every sentence earns its place and there is no filler, though the Args restating of names/defaults partially duplicates the schema.

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 a rich output schema and only two optional parameters, the description covers enough to invoke the tool correctly and even summarizes the return shape. The main omission for a tool in this large sibling set is failure to differentiate from capture_viewport.

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%, so the description must compensate, and it largely does: both parameters are documented with defaults, and the enum value 'full' vs 'fast' is explained in terms of the underlying capture path. Minor gap is that max_size is only described as 'maximum size for the largest dimension' with no note on whether it preserves aspect ratio or whether 0 disables scaling.

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 specific verb and resource: capturing a screenshot of the current Blender 3D viewport. The scope ('current viewport') is clear. However, it does not distinguish itself from the sibling tool 'capture_viewport', which an agent could easily confuse with this 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 description implicitly guides the fast-vs-full choice by explaining each mode ('instant viewport capture using OpenGL' vs 'complete render through the active render engine'), which is real usage value. But it gives no explicit when-to-use-this-instead-of-capture_viewport guidance, leaving the agent to guess between two similarly named siblings.

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