Skip to main content
Glama
sketchup-mcp2

sketchup-mcp2

by zinin

export_scene

Exports the current SketchUp scene to a temporary file in skp, obj, dae, stl, png, or jpg format for sharing or further processing.

Instructions

Export the current scene to a temp file on the SketchUp host.

Formats: skp (native), obj / dae / stl (geometry), png / jpg (viewport render, default 1920×1080). The file is written on the machine running SketchUp — on a split-host setup the path is not directly readable here. An untitled model cannot be exported to skp (-32602) — the user must save it first; other formats work.

Returns: JSON {path, format}.

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": "export_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoskp (native), obj / dae / stl (geometry), png / jpg (viewport render)skp

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / format / description
      Added value: +"skp (native), obj / dae / stl (geometry), png / jpg (viewport render)"
  2. First observedv0.0.1

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the file lands on the SketchUp host (not locally), the error code -32602 and its cause for skp on untitled models, that other formats still work in that state, and the default 1920×1080 render size. These are non-obvious failure modes an agent could not get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The purpose leads, followed by a grouped format list, host caveat, error condition, and return shape. Every line adds information; nothing is padded.

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?

An output schema exists, yet the description still names the return shape ({path, format}) briefly without over-explaining. For a single-parameter tool with meaningful host/config caveats, all decision-relevant context is present.

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 coverage is 100% and the enum is already documented, so the baseline is 3. The description adds value beyond the schema by explaining the png/jpg default resolution and by tying the skp format to the untitled-model error, which the schema alone does not convey.

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?

"Export the current scene to a temp file on the SketchUp host" gives a specific verb, resource and destination. It doesn't explicitly differentiate from the closest sibling, get_viewport_screenshot, so an agent must infer the difference (file on disk vs. inline image) from the format list.

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?

The split-host caveat ("the path is not directly readable here") effectively tells the agent when this tool's output is unusable in the current context, and the untitled-model note states a precondition. It stops short of naming an alternative tool for the viewport-render case.

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