Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

hm_listing

Fetch an H&M category product listing with prices, images, colors, and per-size stock. Paginate by page, sort results, and filter new items.

Instructions

Browse an H&M category's product listing. Returns one H&M category's product listing page: products with pricing, images, colors, and per-size stock. category_id is an H&M category slug (e.g. ladies_newarrivals_all, men_newarrivals_all, ladies_jeans) -- there is no category/nav-tree discovery endpoint, so category_id values come from known H&M storefront paths rather than a lookup call. Pagination is page-based and real: requesting a page beyond the category's real last page returns a normal response with an empty products array rather than an error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number, one-based, defaults to 1
sortNoSort order, defaults to RELEVANCE
is_newNoOptional filter for newly added items only
page_sizeNoResults per page, 1 to 72, defaults to 36
category_idYesH&M category slug

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.5
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "RELEVANCE",
+  "NEWEST_FIRST",
+  "PRICE_ASCENDING",
+  "PRICE_DESCENDING"
+]
  2. Addedv1.14.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does so well: it discloses the return contents (products with pricing, images, colors, per-size stock) and a real edge case — an out-of-range page returns a normal response with an empty products array rather than an error. That pagination behavior is exactly the kind of non-obvious trait an agent needs, though auth/rate-limit context is absent.

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 the purpose, then progressively adds value: return contents, category_id sourcing, and pagination behavior. Each sentence contributes. There is minor redundancy between the opening 'Browse an H&M category's product listing' and the following 'Returns one H&M category's product listing page', which keeps it from a 5.

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?

No output schema exists, so the description must describe returns — and it does (pricing, images, colors, per-size stock). With five parameters, one enum, and no annotations, the coverage of purpose, parameter sourcing, and pagination semantics is solid. Missing only ancillary details like rate/response-shape specifics.

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 the baseline is 3, but the description adds real meaning beyond the schema: category_id examples (ladies_newarrivals_all, men_newarrivals_all, ladies_jeans) and the critical caveat that no discovery endpoint exists. It also documents page-based pagination semantics. This exceeds what the schema alone provides.

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: "Browse an H&M category's product listing" and clarifies it returns a single category's listing page. An agent can distinguish this from hm_search (keyword search) and hm_product (single item) by the category-scoped framing. It stops short of explicitly naming a sibling, so it lands at 4 rather than 5.

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?

Provides genuine usage context: it explains that category_id must come from known H&M storefront paths because there is no category/nav-tree discovery endpoint. This tells the agent how to source the required parameter instead of guessing. It does not give an explicit when-to-use-this-instead-of-hm_search rule, so it is not a 5.

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