Skip to main content
Glama
architectural_modeling_workflow

architectural_modeling_workflow

by Lsc1123

sketchup_scene

Destructive

Select an existing scene or save a specific camera view on request, without cluttering the model with diagnostic scenes. Use it to switch or preserve named views.

Instructions

Select an existing scene or save one explicitly requested camera; does not create diagnostic scene clutter.

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": {
      "expected_revision": "<expected_revision>",
      "operation_id": "<operation_id>"
    },
    "name": "sketchup_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
cameraNo
selectNo
operation_idYes
expected_revisionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

C2.8/5.0
Behavior2/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates the document, yet the description never says what is mutated or lost — changing the active scene presumably alters viewport/camera state, and saving a camera persists it. With zero schema coverage and a destructive flag, the description should disclose the revision/operation_id contract and the state-change consequences, and it does not.

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?

A single compact sentence with the primary capability front-loaded; nothing is padded. The closing negated clause is terse but earns its place by warning against clutter creation, though its phrasing is muddier than it needs to be.

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

Completeness2/5

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

Five parameters, two of them required (expected_revision, operation_id), with zero schema description coverage and a destructive annotation — this is a complex contract that the one-line description does not address at all. The output schema covers return values, but the mutation semantics, revision guard, and operation_id purpose remain unexplained.

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?

No parameters are described in the schema (coverage 0%), but this is a zero-parameter tool, so the baseline of 4 applies. The description's mention of "diagnostic scene clutter" is slightly misleading given the tool does not create diagnostic artifacts; the clause is more about avoiding unnecessary scene creation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Select an existing scene or save one explicitly requested camera" does pair a verb with a resource, but the two halves describe different operations without saying how they relate, and the trailing clause about "diagnostic scene clutter" is ambiguous scope language rather than purpose. An agent can infer this manages SketchUp scenes, but not precisely what it does in a single call.

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

Usage Guidelines2/5

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

There is one implicit exclusion ("does not create diagnostic scene clutter") which hints the tool should not be used for speculative scene creation, but no explicit when-to-use conditions, no prerequisites, and no named alternative such as sketchup_capture or sketchup_query for reading viewport state. Guidance is essentially absent.

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