Skip to main content
Glama

Search Products By Image URL

products.search.image_url
Read-only

Search a fashion catalog by image URL and return visually similar products with sizes, pricing, and purchase links. Apply optional filters for gender, size, price, or brand.

Instructions

Search PoloPan catalog products using visual image similarity from a publicly accessible image URL with optional multi-attribute filters. Returns visually similar products with available sizes, pricing, and verified purchase URLs (https://s.polopan.com/p/{handle}).

PURPOSE & DISAMBIGUATION:

  • Performs reverse visual search using computer-vision embeddings for a remote image URL.

  • Distinct from 'products.search.text': Use this tool when you have an image URL, NOT for textual keyword queries.

  • Distinct from 'products.search.image_upload': Use this tool for publicly hosted HTTP(S) image URLs, NOT for local file paths or base64 data.

  • Distinct from 'vision.outfit.detect_pieces': Use this tool to search catalog items matching an entire single-garment image, NOT for segmenting multi-garment influencer photos into bounding boxes.

WHEN TO USE:

  • When the user shares a web link to an image (e.g. Pinterest, Instagram, blog post) and wants to find visually matching products in the PoloPan catalog.

WHEN NOT TO USE:

  • Do NOT use when the image is stored on local disk or as base64 data (use 'products.search.image_upload').

  • Do NOT use when searching by text descriptions (use 'products.search.text').

  • Do NOT use when you need to crop/isolate individual outfit pieces from a full-body model photo (use 'vision.outfit.detect_pieces').

BEHAVIOR & SAFETY:

  • Read-only and idempotent with no persistent state modifications.

  • Downloads the image, generates visual embeddings, and retrieves ranked catalog matches.

  • Enriches all returned items with verified PoloPan purchase links and stock metadata.

PARAMETERS & CONSTRAINTS:

  • 'image_url' (string, required): Publicly accessible HTTP(S) URL of the image to search for visual matches.

  • 'page' (integer >= 1, default 1): Pagination page number.

  • 'page_size' (integer 1-100, default 20): Number of candidate items returned per page.

  • 'sort_by' (enum, default 'relevance'): Ranking attribute ('relevance', 'price', 'title').

  • 'sort_order' (enum, default 'desc'): Sort order ('asc' or 'desc').

  • 'gender' (string, optional): Target gender filter ('men', 'women', or 'unisex').

  • 'size' (array of strings, optional): Filter by available size labels.

  • 'price_min' (number, optional): Minimum price threshold.

  • 'price_max' (number, optional): Maximum price threshold.

  • 'vendor' (array of strings, optional): Brand filter array.

  • 'personalize' (boolean, default false): Whether to apply personalized ranking weights.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number for pagination (1-indexed)
sizeNoArray of sizes to filter by (e.g. ['S', 'M', 'L'])
genderNoTarget gender filter: 'men', 'women', or 'unisex'
vendorNoList of brand names to filter by
sort_byNoSorting criteria for search results: 'relevance', 'price', or 'title'relevance
image_urlYesPublicly accessible HTTP(S) URL of the fashion image to search for visual matches
page_sizeNoNumber of items to return per page (1 to 100, default 20)
price_maxNoMaximum price in local currency
price_minNoMinimum price in local currency
sort_orderNoSort order: 'asc' for ascending, 'desc' for descendingdesc
personalizeNoWhether to apply personalized ranking based on user style profile

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.5

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark readOnlyHint=true and destructiveHint=false; the description reinforces this and adds process details ('downloads the image, generates visual embeddings, retrieves ranked catalog matches') and output enrichment ('verified PoloPan purchase links and stock metadata'). No contradiction with 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?

The description is organized into labeled sections with a front-loaded summary, and the disambiguation/usage sections are highly actionable. Minor redundancy: the parameter list duplicates the input schema, adding length without new information.

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?

Given 11 parameters, no output schema, and several near-sibling tools, this description is comprehensive: it covers purpose, exclusions, behavior, safety, return contents, and parameter constraints. It even names the exact purchase URL pattern so agents know what result links will look like.

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 description coverage is 100%, so the input schema already documents all 11 parameters. The description's PARAMETERS & CONSTRAINTS section restates defaults, types, and bounds without adding deeper semantics beyond what the schema provides. Baseline 3 is appropriate.

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 ('search'), resource ('PoloPan catalog products'), and mechanism ('visual image similarity'), then explicitly disambiguates from products.search.text, products.search.image_upload, and vision.outfit.detect_pieces. An agent can tell it apart from siblings immediately.

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

Usage Guidelines5/5

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

Provides explicit WHEN TO USE and WHEN NOT TO USE sections with sibling tool names and conditions: public URL vs local/base64, image URL vs text query, single garment vs multi-piece outfit. No inference is required.

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