Skip to main content
Glama
ApparelHub-AI

apparelhub-mcp

Official

get_design_collection

Read-only

List sibling designs produced in the same generation as a given design, with titles, concept descriptions, and background state, to build products from the full themed set.

Instructions

List the OTHER designs that came out of the same generation as this one. When generate_image is called with concepts > 1, one generation produces a themed set; every design is saved separately and this is how you find its siblings. The design you ask about is never included, and the list is oldest first. An ordinary design returns an empty list, which is the honest answer, not an error (an inaccessible or unknown uuid also reads as empty, so an empty list does not prove the design exists). Read-only and not metered. Each entry carries title and concept_description: the product name and retail description the model wrote for that concept. Use them to build products without asking the merchant to retype copy the model already produced; either may be null and must never be invented. background_state says whether the design can be lifted off its background: transparent is ready to place, opaque_box can be keyed automatically (process_transparency), opaque_varied cannot be separated and will print WITH its background. Asked for a set, the model often answers with pictures of finished garments rather than flat art, and building a product from one prints a garment onto a garment, so do NOT build a product from an opaque_varied design without telling the user it will print with its background. Do not describe it as "a photograph" either: legitimately textured art reports opaque_varied too.

[#f2d543]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workspaceNoWorkspace uuid (agency accounts).
design_uuidYesAny design from the generation (usually the image_uuid generate_image returned).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.16.2

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations it adds substantial context: 'not metered', self-exclusion, oldest-first ordering, and the crucial disclosure that an empty list also results from an unknown or inaccessible uuid so it does not prove existence. It also explains what an opaque_varied background_state implies, which is real behavioral disclosure beyond the annotations.

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?

Purpose is front-loaded in sentence one and each block (empty-list semantics, return fields, background_state, product-building caveat) carries distinct value. It is dense and leans into downstream product guidance that is only tangentially about this read, and a stray '[#f2d543]' artifact trails the text.

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

Completeness5/5

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

With no output schema, the description fully compensates by naming the returned fields (title, concept_description, background_state) and explaining each, including nullability and the rule never to invent copy. An agent has everything needed to interpret the response.

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 already 100%, so the baseline is 3, but the description adds meaning: any design in the generation (not just the returned image_uuid) works as the anchor, and the anchor is never included in results. The workspace parameter is not addressed, keeping it from a 5.

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?

The opening sentence states a specific verb and resource with scope: list the OTHER designs from the same generation. It immediately distinguishes itself from list_my_designs and the design CRUD siblings by defining the generation-set relationship, and even states the self-exclusion rule.

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 clearly frames the triggering scenario (generate_image with concepts > 1) and gives downstream guidance about not building products from opaque_varied without warning the user. However, it never names an alternative tool (e.g., list_my_designs) or states explicit when-not-to-use conditions, so routing against siblings is inferred rather than stated.

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

Deploy Server

Other Tools