Skip to main content
Glama
CLO Atelier

CLO Atelier

by benproj

Save or export the project

clo_export

Export the open CLO 3D session to disk as a project, garment, 3D mesh, 2D patterns, techpack, turntable images, or avatar at a specified path and format.

Instructions

Write the current work to disk, overwriting any file at that path. zprj saves the whole project; zpac the garment only; obj/fbx/glb/gltf the 3D mesh; dxf the 2D patterns; pattern-json CLO's pattern data; techpack a .json with images alongside; turntable a rotating image sequence (give a .png path); avatar an .avt.

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": {
      "format": "<format>",
      "file_path": "<file_path>"
    },
    "name": "clo_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatYes
file_pathYesAbsolute output path, including the extension.
timeout_sNoSeconds to wait for CLO before giving up.
include_avatarNoFor mesh formats: include the avatar as well as the garment (default false).
turntable_imagesNoFor turntable: number of images around 360 degrees (default 8).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose the critical trait: it overwrites whatever exists at the path, which is a destructive side effect an agent must know. It also adds format-specific behavior not derivable elsewhere (turntable needs a .png path, techpack emits a .json with images alongside, avatar writes .avt). It does not say what is returned on success/failure or what happens if the directory is missing.

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?

One front-loaded sentence states the action and the destructive consequence; the semicolon-chained format glossary is compact and scannable with zero filler. Every clause adds information an agent needs to choose a format.

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?

For a 5-parameter export tool with no output schema and no annotations, the definition covers format selection, the required path, and destructive behavior adequately. The remaining gap is return behavior and error conditions, which nothing else in the supplied metadata supplies.

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 80%, so the baseline is 3, but the description materially exceeds it by explaining each enum member of `format` beyond the bare value list. The turntable '.png path' constraint adds real meaning that the schema does not express. It stays silent on timeout_s and include_avatar, which the schema already documents.

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

Purpose5/5

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

States a concrete verb and effect — 'write the current work to disk, overwriting any file at that path' — and then enumerates every supported output format with what each one actually saves (whole project vs garment vs mesh vs 2D patterns). An agent can tell this is the export/save counterpart to clo_open_file 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?

The per-format breakdown effectively tells the agent which option to pick for a given intent (project-wide vs garment-only vs mesh vs pattern data), which is the main usage decision here. It stops short of explicit exclusions or prerequisites, e.g. whether a save is required before export or when to prefer one mesh format over another.

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