Skip to main content
Glama

Upload Clothing from URL

upload_garment_from_public_url

Upload Clothing from public HTTP(S) image URLs. Queues a recoverable batch upload and returns an operation immediately; retry with the exact same arguments to read its state (a retry creates no second upload). Photos are stored as uploaded, without background removal; processing_mode is ignored. Prefer assets with {asset_kind: full|detail, asset_view: front|back|side, asset_url}; exactly one full front is required, every full view is unique, and detail views can repeat. No base64, chat file objects, or local paths.

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": "upload_garment_from_public_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoSingle garment name
assetsNoSingle garment full asset set. Use asset_kind/asset_view. Exactly one full front is required; full views are unique and detail views can repeat.
genderNoSingle garment gender: male, female, unisex
board_idNoThe open Shoot Board's board_id, from Open Shoot Board or your context.
garmentsNoGarments to upload from public HTTP(S) URLs. No chat file objects and no base64.
file_nameNoSingle original file name
image_urlNoSingle public HTTP(S) front image URL
mime_typeNoSingle MIME/content type, e.g. image/png
descriptionNoSingle item-level garment description hint
back_image_urlNoSingle optional public HTTP(S) back image URL
side_image_urlNoSingle optional public HTTP(S) side image URL
processing_modeNoOptional image processing. 'background_removal' removes the background (the platform upload default); 'none' stores the image as-is. Omit to use background removal.
detail_image_urlsNoSingle optional public HTTP(S) detail image URLs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / board_id
      Added value: +{
      +  "description": "The open Shoot Board's board_id, from Open Shoot Board or your context.",
      +  "type": "string"
      +}
    • addedInput schema / required
      Added value: +[]
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare write/open-world/safety hints; the description adds substantively: asynchronous queue semantics with immediate operation return, retry-as-poll behavior that creates no second upload, no background removal, processing_mode ignored, and rejected input forms. It even overrides the schema's claim that 'background_removal' is the platform default, which is high-value behavioral correction. The retry-dedup statement sits in mild tension with idempotentHint=false but reads as an operation-polling special case rather than a flat contradiction.

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?

Four dense sentences, purpose front-loaded, no filler or repetition of the title. It is packed enough that the asset-shape and validity rules compete for attention with the async/retry contract, but every clause carries information an agent needs.

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 13-parameter, nested-typedef tool with no output schema and only safety annotations, the description covers the operational contract (async operation, retry/poll, no background removal), the accepted input surface, and asset validity rules. Gaps: no mention of the required board_id source, no guidance on how/when to check operation status beyond 'retry', and no per-field guidance for the legacy shortcut parameters.

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 description coverage is 100%, so the baseline is 3, but the description adds cross-field validation semantics the schema does not state as rules: 'exactly one full front is required, every full view is unique, and detail views can repeat', plus the preferred {asset_kind, asset_view, asset_url} shape over deprecated asset_role/legacy shortcuts. It does not mention board_id or the 50-item cap on garments.

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?

Opens with a specific verb+resource+transport: 'Upload Clothing from public HTTP(S) image URLs', and immediately scopes it against sibling upload paths by ruling out 'base64, chat file objects, or local paths' (which separates it from upload_avatar_from_chat_file / save_reference_file_from_chat_file). The batch/operation model ('Queues a recoverable batch upload and returns an operation') further pins down what the tool actually does.

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 conditions for correct use: retry with the exact same arguments to read state, use assets shaped as {asset_kind, asset_view, asset_url}, exactly one full front required, full views unique, detail repeatable. It does not explicitly name an alternative tool for the chat-file/base64 case (it only negates those input forms), so routing guidance is implicit rather than spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources