Skip to main content
Glama
CLO Atelier

CLO Atelier

by benproj

Look at the garment

clo_screenshot
Read-only

Captures rendered images of the 3D garment and 2D pattern layout so you can inspect drape, fit, and piece placement. Request up to six views in one call to review the scene.

Instructions

Capture images of the scene so you can see it. Ask for several views in one call. 3D views other than current move the user's camera. 2d-patterns is a flat layout of the pattern pieces as drawn in the 2D window; the number labels restart for each fabric and are not pattern indices.

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": "clo_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewsNoViews to capture (default: current).
save_dirNoFolder to keep the images in. Defaults to a temporary folder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.1/5.0
Behavior4/5

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

The readOnlyHint annotation implies a safe read, but the description discloses a real side effect beyond the annotation: 3D views other than `current` move the user's camera. It also clarifies the semantics of `2d-patterns` output, which prevents misreading the labels as pattern indices. Not disclosed: how returned images are persisted or referenced after capture.

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?

Three sentences, no filler, with the core purpose front-loaded and the caveats attached to the values they qualify. Every clause carries information an agent needs to call this correctly.

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 no output schema, the description still conveys that images are returned for the agent to view, and it covers the camera side effect and the `2d-patterns` interpretation. The only minor gap is how saved images are referenced after the call, which the save_dir parameter hints at but does not explain.

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%, so baseline is 3, but the description earns above baseline by explaining the meaning of a view value (`2d-patterns` is a flat layout of pattern pieces, and its number labels restart per fabric and are not pattern indices) and by flagging the camera side effect of 3D views. save_dir behavior is left to the schema, which already covers it adequately.

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?

The description opens with a concrete verb and resource: 'Capture images of the scene so you can see it.' That is specific enough to separate it from data-returning siblings like clo_get_scene, though it never names an alternative explicitly. The purpose is clear without opening the schema.

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?

It gives actionable call guidance: 'Ask for several views in one call,' which tells the agent to batch rather than call repeatedly. It also warns that 3D views other than `current` move the user's camera, which implicitly conditions when to use them. There is no explicit exclusion or stated alternative tool, so it falls short of a 5.

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