Skip to main content
Glama

try_on_clothes

Render a person wearing a selected garment by combining a forward-facing person image with a product or worn garment image and specifying the garment category.

Instructions

Render a person wearing a garment (YouCam AI Clothes, cloth-v4). Costs 2 units on success. person_image: one person, facing forward, shoulders visible. garment_image: a front product shot of one garment, or a photo of someone wearing it.

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": {
      "person_image": "<person_image>",
      "garment_image": "<garment_image>",
      "garment_category": "<garment_category>"
    },
    "name": "try_on_clothes"
  }
}

Input Schema

NameRequiredDescriptionDefault
person_imageYesAn https:// image URL on this server's allowlist, or an image_ref (img_...) returned by an earlier call in this session. JPEG or PNG.
wait_secondsNoSeconds to wait for the result before returning a task_ref to poll. Default 60.
garment_imageYesAn https:// image URL on this server's allowlist, or an image_ref (img_...) returned by an earlier call in this session. JPEG or PNG.
garment_categoryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely new context: a cost of 2 units charged only on success, plus the model identifier. It stops short of describing failure handling, refunds, or the returned artifact, so it does not reach 5.

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?

Front-loaded with purpose and cost, then two tight constraint fragments per image parameter. No filler, though the trailing parameter notes read as clipped fragments rather than a coherent structure.

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

Completeness3/5

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

With no output schema, the description should say what comes back — an image, a task_ref, or both — and it does not. It also never routes the agent to get_task_status for polling, which is the obvious follow-up for an async generation call, so a moderate gap remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, so the baseline is 3. The description usefully constrains the content of person_image and garment_image, but garment_category's enum values — notably 'auto' — are left unexplained, and wait_seconds is not addressed at all in the description.

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?

States a concrete verb and resource ('Render a person wearing a garment') and pins the underlying model (YouCam AI Clothes, cloth-v4). The garment domain implicitly separates it from the hair and skin siblings, but no sibling is named explicitly, so it falls just short of 5.

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?

Gives input prerequisites (one person, facing forward, shoulders visible; front product shot) but no when-to-use vs when-not guidance, no mention of the alternative of polling get_task_status, and no statement about what to do if wait_seconds expires. Usage 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.