Skip to main content
Glama

capture_screenshot

Capture a Houdini viewport or pane tab image to disk, with an optional settle delay so Karma renders converge before the screenshot is saved.

Instructions

Capture a screenshot of the viewport or a specific pane tab.

The image is written to disk only; open output_path with your file reader to look at it. Prefer get_geometry_info, get_node_info or get_scene_summary unless visual confirmation is genuinely needed. The frame is the viewport's own size and view. For a set size, render_viewport(resolution=...); to frame one object first, frame_all(node_paths=...), and for frames of one scale across a comparison sheet, frame_all(bounds=...) with the same box before each capture. A Scene Viewer capture names the network it shows (viewer_network); viewer_note says when that is a DOP network, drawn as the simulation's objects rather than the SOP display, or a SOP subnet, drawn as its own display node rather than the object's output; visible_objects_note, when the viewport's Visible Objects pattern leaves out the object the viewer is in, so the frame shows none of it.

Args: output_path: Image file path; variables ($JOB) are expanded. Default: a new PNG in the temp dir. pane_name: Pane tab name. settle_seconds: Wait this long before capturing, without blocking Houdini, so a Karma viewport can converge after a change. Use this instead of a shell sleep between calls. Capped at 120.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "capture_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
pane_nameNo
output_pathNo
settle_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.24.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / output_path / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / output_path / default
      Added value: +null
    • removedInput schema / properties / output_path / type
      Removed value: -"string"
    • removedInput schema / required
      Removed value: -[
      -  "output_path"
      -]
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations present, the description carries the full burden and does so well: it discloses that the image is written to disk only and must be read back via output_path, that the frame is the viewport's own size/view, that settle_seconds waits without blocking Houdini, and that the value is capped at 120. It also explains non-obvious capture semantics for Scene Viewer frames (DOP network vs SOP subnet rendering, Visible Objects exclusion).

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 one-line purpose, then usage routing, then framing hints, then an Args block, with zero filler sentences. The Scene Viewer network/note explanation is dense and only conditionally relevant, which costs a little crispness.

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

Completeness5/5

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

There is no output schema and no annotations, yet the description covers the return artifact (a file on disk that must be opened), timing/settling semantics, framing alternatives, and viewport-specific caveats. An agent has everything needed to call it correctly and interpret the result.

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 mostly does: output_path gains variable expansion ($JOB) and a default temp-dir PNG, settle_seconds gains purpose (Karma convergence), non-blocking behavior, the 'use instead of a shell sleep' guidance, and the 120 cap. pane_name only gets 'Pane tab name', which is thinner than the others.

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 ('Capture a screenshot of the viewport or a specific pane tab'), making the scope unmistakable. It does not explicitly distinguish itself from the sibling capture_network_editor, but the viewport/pane-tab framing makes the boundary reasonably clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicitly says to prefer get_geometry_info, get_node_info or get_scene_summary 'unless visual confirmation is genuinely needed', naming the alternatives and the condition that selects them. It goes further, routing agents to render_viewport for a fixed size and frame_all for framing an object or matching scale across a sheet.

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