A1 Yandex KIT MCP

List variants

list_variants

Read-only

List sellable SKUs from the catalog with optional filters and pagination, and produce CSV exports. Detects and reports unsupported archived-status filters to prevent misleading partial results.

Instructions

Primary sellable catalog/export listing: list variants (SKUs), one item per sellable SKU. Use this for ordinary catalog or «выгрузи товары в CSV» requests; use list_products only for an explicit raw product-group export. Variants support optional filters and pagination. By default the API returns variants of all statuses except ARCHIVED. format:"csv" defaults to top-level scalar fields and serializes nested pricing/stocks as JSON cells; it does not create flat price or per-warehouse stock columns. Known KIT API defect: ARCHIVED is silently stripped from the status filter, so archived variants cannot be listed (only read by ID via get_variant); the tool detects this and fails with STATUS_FILTER_IGNORED, ARCHIVE_READ_UNSUPPORTED or MIXED_ARCHIVED_FILTER_UNSUPPORTED (for filters mixing ARCHIVED with other statuses) instead of returning the wrong catalog slice. For storefront page URLs use list_variant_links — it joins each item's relative_link_url with the store's b2c_url for you. The response carries a machine-readable coverage envelope (coverage, received, total_count, pages_read); coverage:"partial" MUST be reflected in the user-facing answer and forbids claiming the listing is complete.

Input Schema

TableJSON Schema

Name	Required	Description
`all`	No	Fetch pages via auto-pagination, up to 500 items; inspect coverage and continue with explicit page reads if coverage is partial; ignores page/per_page.
`name`	No	Case-insensitive partial search by name, SKU, barcode or KIT ID.
`page`	No	Page number, starting at 1 (default 1).
`fields`	No	CSV columns; only valid together with format:"csv". Field names are validated against the item schema of the operation's response — an unknown name fails with the list of allowed fields. Default: every top-level scalar field of the item.
`format`	No	Output format: "csv" renders the items as RFC 4180 CSV (a leading "# coverage:" comment line, then the header row) instead of JSON — cheaper for wide exports. Default: JSON.
`status`	No	Filter by variant status.
`per_page`	No	Items per page, 1-100 (default 25). Values outside the range are clamped.
`product_id`	No	Filter by parent product ID (UUID).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.6.2Sep 8, 2026

changedInput schema / properties / all / description

Previous value: -"Fetch all pages via auto-pagination, up to 500 items; ignores page/per_page."New value: +"Fetch pages via auto-pagination, up to 500 items; inspect coverage and continue with explicit page reads if coverage is partial; ignores page/per_page."

Changed2 schema fields changedv1.6.0Sep 8, 2026

addedInput schema / properties / fields

Added value: +{
+  "description": "CSV columns; only valid together with format:\"csv\". Field names are validated against the item schema of the operation's response — an unknown name fails with the list of allowed fields. Default: every top-level scalar field of the item.",
+  "items": {
+    "type": "string"
+  },
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / properties / format

Added value: +{
+  "description": "Output format: \"csv\" renders the items as RFC 4180 CSV (a leading \"# coverage:\" comment line, then the header row) instead of JSON — cheaper for wide exports. Default: JSON.",
+  "enum": [
+    "csv"
+  ],
+  "type": "string"
+}

First observedv1.3.0Aug 10, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses rich behavioral details: default status filtering excludes ARCHIVED, CSV output serializes nested cells rather than flat columns, and the known KIT defect causes explicit error codes instead of a misleading catalog slice. It also explains the coverage envelope and how partial coverage must be reflected in user-facing answers.

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 dense and front-loaded, starting with the tool's primary purpose and then adding usage, CSV behavior, the API defect, sibling routing, and response coverage expectations. It is longer than typical descriptions, but nearly every sentence carries load-bearing operational guidance; only the detailed defect explanation could be trimmed without losing essential warning value.

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?

For a read-only, high-complexity listing tool with 8 optional parameters und no output schema, the description covers purpose, selection criteria, defaults, CSV semantics, failure modes, error codes, sibling alternatives, and response-contract caveats. Nothing an agent needs to invoke this correctly and interpret the result is 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?

The input schema already documents every parameter, so the baseline is 3; the description adds extra meaning by clarifying defaults and interactions: the default status exclusion, csv format applicability, and the coverage semantics of the 'all' flag. It does not restate each parameter, but credits the agent with meaningful behavior above the schema's information.

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 opens by naming the concrete resource and scope: 'list variants (SKUs), one item per sellable SKU' and calls it the 'Primary sellable catalog/export listing'. It also distinguishes itself from list_products and list_variant_links, so an agent can tell siblings apart 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?

The description gives explicit routing guidance: use this tool for 'ordinary catalog or «выгрузи товары в CSV» requests', use list_products only for an explicit raw product-group export, and use list_variant_links for storefront page URLs. It also warns against listing archived variants, a clear when-not-to-use condition.

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

Deploy Server

List variants

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools