Skip to main content
Glama
CLO Atelier

CLO Atelier

by benproj

Create pattern pieces

clo_create_patterns

Draw one or more 2D pattern pieces from ordered outline points and create all garment pieces in a single call, using absolute coordinates and returning outlines ready for sewing.

Instructions

Draw one or more new pattern pieces from ordered outline points (each outline closes back to its first point). Create all pieces of a garment in one call. Coordinates are absolute positions in the 2D window, so give each piece its own area or they overlap. Returns each new piece's index and its outline lines (index, length), ready for clo_sew.

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": {
      "patterns": "<patterns>"
    },
    "name": "clo_create_patterns"
  }
}

Input Schema

NameRequiredDescriptionDefault
patternsYes

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, the description carries the load and does well: it discloses that each outline auto-closes to its first point, that coordinates are absolute in the 2D window with overlap consequences, and what the call returns (piece index plus outline lines with index and length). It omits whether creation is undoable, what happens on invalid or self-intersecting outlines, and any permission or state preconditions.

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?

Four tightly packed sentences, front-loaded with what the tool does, then batching advice, then the placement constraint, then the return shape. No filler and nothing restated from the schema verbatim.

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 single-parameter geometry-creation tool with no annotations and no output schema, the description covers creation semantics, overlap risk, and return values well enough to invoke it correctly. A sentence on default fabric/layer behavior or failure modes would close the remaining gap.

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?

The schema documents the nested point/name/layer/fabric fields, so the description needn't repeat them; instead it adds genuine meaning about the points array — drawing order, automatic closing, and absolute-window placement. It leaves the layer and arrangement_point semantics entirely to the schema, which is acceptable but a missed chance to clarify collision behavior.

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 specific verb and resource ('Draw ... new pattern pieces from ordered outline points') and scopes it as creating NEW geometry, which distinguishes it from clo_edit_pattern and clo_copy_pattern by name alone. The downstream link to clo_sew further pins its role in the workflow.

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?

Gives clear operational guidance for batching ('Create all pieces of a garment in one call') and a placement precondition ('give each piece its own area or they overlap'). It does not explicitly say when to prefer clo_edit_pattern or clo_copy_pattern over re-creating geometry, so the when-not side is implied rather than stated.

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