Skip to main content
Glama
architectural_modeling_workflow

architectural_modeling_workflow

by Lsc1123

sketchup_script

Destructive

Execute trusted Ruby scripts inside a native SketchUp transaction to create or modify geometry while declaring scopes, new roots, and scene names for controlled workspace changes.

Instructions

Run trusted workspace Ruby inside a native transaction. Do not manage transactions or change documents/edit context in scripts. Declare existing geometry scopes, any new roots and scene names. This is code execution, not an OS sandbox.

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": {
      "script": "<script>",
      "scope_ids": "<scope_ids>",
      "expected_revision": "<expected_revision>",
      "operation_id": "<operation_id>",
      "purpose": "<purpose>"
    },
    "name": "sketchup_script"
  }
}

Input Schema

NameRequiredDescriptionDefault
scriptYes
purposeYes
scope_idsYes
scene_namesNo
operation_idYes
expected_revisionYes
allow_new_root_entitiesNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.6/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and openWorldHint=true, but the description adds context they cannot: the script runs wrapped in a native transaction (so the caller must not open one), it executes trusted workspace code rather than being OS-sandboxed, and it must declare scopes/new roots/scene names up front. What is not covered is failure behavior, rollback semantics, or limits on script runtime.

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?

Four short sentences with no filler, and the core behavior plus the transaction prohibition are front-loaded. The third sentence is compressed to the edge of ambiguity — "any new roots" is a terse rendering of allow_new_root_entities that an agent may not connect to the parameter without rereading the schema.

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

Completeness3/5

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

An output schema exists, so return values need not be explained. But this is a destructive, open-world code-execution tool with 7 undocumented parameters, and the description omits what expected_revision and operation_id are for, when the call fails, and whether a failed script rolls back — meaningful gaps for a tool of this risk level.

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% across 7 parameters, so the description must carry the load and it only partly does. "Declare existing geometry scopes, any new roots and scene names" maps to scope_ids, allow_new_root_entities, and scene_names, but expected_revision, operation_id, and purpose — three required parameters — are given no meaning at all, and the concurrency/idempotency intent behind the revision and operation id is left unstated.

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?

"Run trusted workspace Ruby inside a native transaction" names a specific verb (execute) and resource (Ruby in the SketchUp workspace), and the closing line "This is code execution, not an OS sandbox" sharpens the distinction from a generic sandbox/runner. It is clearly separable from siblings like sketchup_create or sketchup_edit_context, though it never names an alternative explicitly.

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?

There is real when-not guidance for what the script must not do: "Do not manage transactions or change documents/edit context in scripts." However, the agent is never told when to reach for this tool versus sketchup_create, sketchup_edit_context, or sketchup_transform, so tool selection still has to be inferred from the name.

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