Skip to main content
Glama

Good Turn Studio (all tools)

by io.github.GoodTurnStudio
OverviewDiscussionsAdmin

Wardrobe Connect: Find clothes that look like a picture

wardrobeconnect_find_clothes_by_image
Read-onlyIdempotent

Wardrobe Connect. Find clothes that look like a picture of one item. Takes the picture's direct https link and, if wanted, a few words naming the item, a size, a price limit, the condition and a country; it needs nothing else from the conversation. Returns visually similar eBay listings from the Clothing, Shoes and Accessories category only, in eBay's look-alike order. If the picture does not show one piece of clothing, matches is empty and the say line asks what the item is. A short item name in q makes the results match it, which removes look-alikes of the wrong kind.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoWhich item in the picture, in a few words, for example "the camel coat".
sizeNoClothing or shoe size to match, for example M, 10 or UK 8.
countryNoTwo-letter country code for the eBay site and currency. Defaults to where the request comes from.
conditionNoCondition: any, new or used.
image_urlYesDirect https link to one JPEG, PNG or WebP picture, 6 MB at most.
max_priceNoHighest price, in the local currency.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"Two-letter country code for the eBay site and currency, for example US or GB."New value: +"Two-letter country code for the eBay site and currency. Defaults to where the request comes from."
    • addedInput schema / properties / country / enum
      Added value: +[
+  "US",
+  "GB",
+  "IE",
+  "CA",
+  "AU",
+  "DE",
+  "FR",
+  "IT",
+  "ES"
+]
    • changedInput schema / properties / image_url / description
      Previous value: -"Direct https link to a JPEG, PNG or WebP picture, 6 MB at most."New value: +"Direct https link to one JPEG, PNG or WebP picture, 6 MB at most."
    • addedInput schema / properties / image_url / format
      Added value: +"uri"
    • addedInput schema / properties / image_url / maxLength
      Added value: +2048
    • addedInput schema / properties / max_price / minimum
      Added value: +0
    • changedInput schema / properties / q / description
      Previous value: -"Which item in the picture, for example \"the camel coat\". Results must match it, and it is used as a fallback text search."New value: +"Which item in the picture, in a few words, for example \"the camel coat\"."
    • addedInput schema / properties / q / maxLength
      Added value: +60
    • addedInput schema / properties / size / maxLength
      Added value: +20
  2. Changed1 schema field changed
    • changedInput schema / properties / condition / description
      Previous value: -"any, new or used."New value: +"Condition: any, new or used."
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description still adds genuine behavioral context beyond them: results are restricted to the eBay Clothing/Shoes/Accessories category, returned in look-alike order, and `matches` is empty when the picture isn't a single garment.

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 and each sentence conveys distinct information (purpose, params, return format, edge case). The middle sentence enumerating optional params is long and run-on, and the leading brand tag 'Wardrobe Connect.' is minor filler, but there is no outright redundancy.

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?

With no output schema, the description carries the return burden and does so: it names the source, category restriction, ordering, and the empty-matches edge case plus the clarifying follow-up. Missing only secondary details like result count or pagination behavior.

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 100%, so baseline is 3. The description adds real semantics on top: the optional params are framed as refinements ('if wanted'), and it explains the behavioral effect of `q` (it makes results match the named item and removes look-alikes of the wrong kind) and that country controls site/currency with a default.

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 specific verb and resource (find clothes that look like a picture of one item) and clearly establishes the image-input mechanism. It distinguishes itself functionally from the text sibling wardrobeconnect_find_clothes by requiring a picture link, but never names or contrasts that sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage by describing what the tool 'takes' (an https picture link plus optional refinements) and notes 'it needs nothing else from the conversation.' However, it gives no explicit when-to-use/when-not and never routes the agent to the text-search sibling for cases without an image, leaving the choice to inference.

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

All Good Turn Studio (all tools) toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources