Skip to main content
Glama
neuratechcompany-ops

Kettu Marketplace Intelligence

WB Catalog Categories

wb_categories
Read-onlyIdempotent

Explore the Wildberries catalog hierarchy to find product categories and retrieve the shard and query selectors needed for category feed queries.

Instructions

Browse the Wildberries catalog tree.

Use this to discover what exists before searching: wb_search needs a query string, but a shopper's question is often "what categories of humidifiers are there?". Each node carries WB's own shard and query selectors, which are the addressing needed to pull a category feed.

The live menu is ~800 KB, so responses are always a bounded slice — start at 'top', then expand the branch you care about.

Error Format

On validation or transport/parse failure, raises ToolError with a JSON message describing the error code and whether it is retryable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rootNo'top' for the top-level sections, or a category name / URL path / id to expand (e.g. 'Электроника', '/catalog/elektronika', '8126').top
max_depthNoHow many levels below the root to include. 1 = direct children only.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
metaNoValidation metadata.
rootNoRequested root: 'top' or the resolved category name.
itemsNoCategory nodes at the requested root.
host_usedNoStatic CDN host that served the menu.
max_depthNoDepth limit applied to this response.
truncatedNoWhether the slice was cut short by node limits.
total_returnedNoTotal nodes in the returned slice.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.2.2

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds genuinely useful behavioral context beyond those hints: the live menu is ~800 KB, responses are always a bounded slice, and errors are raised as ToolError with a JSON message indicating retryability. This gives an agent a clear expectation for size and failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, well-structured, and front-loaded with the core purpose. Every sentence contributes: the use case, the contrast with search, the shard/query relevance, the size constraint, and the error format are all useful with no filler.

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 the output schema and rich annotations, the description is complete for an agent to select and call the tool correctly. It covers purpose, when to use it, how to navigate the large tree, response bounding, and error behavior. No critical operational detail appears missing.

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 descriptions of root and max_depth already handle parameter meaning. The tool description adds strategic context by explaining why the bounded slice exists and recommending an iterative expand-from-top approach, which makes the parameters' intended usage clearer than the schema alone.

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?

The description states a specific verb ('Browse') and resource ('the Wildberries catalog tree'), and clarifies its role versus wb_search by noting that wb_search needs a query string while this tool lets a shopper discover categories. It also explains that nodes expose shard/query selectors for pulling a category feed, distinguishing it from feed/product tools.

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?

The description explicitly says when to use this tool ('before searching') and contrasts it with wb_search, which needs a query string. It also advises starting at 'top' and expanding the branch of interest. However, it does not explicitly mention the sibling wb_category_products as the follow-up tool for pulling a feed, though that is implied by mentioning shard/query selectors.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/neuratechcompany-ops/kettu-marketplace-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server