Skip to main content
Glama

Yandex Market Search

yandex_search
Read-onlyIdempotent

Search Yandex Market products and return current prices, ratings, and sellers for Russian-market queries, enabling price comparison and offer checks.

Instructions

Search Yandex Market and return products with both prices, ratings and sellers.

Yandex Market aggregates many sellers per product, which makes it the best single source for "what does this cost right now" across the Russian market — including goods Wildberries and Ozon do not carry.

Each result reports price_rub (what anyone pays — the price the SERP snippet's cart button charges, cross-verified against product cards) and price_with_plus (a conditional price: paying with Yandex Pay, earlier Yandex Plus). Prefer price_rub when quoting a price to a person; price_old_rub is the struck-through reference price and must never be quoted as the price.

A search row describes the SERP snippet's offer, which may be a different member of the product family than the offer yandex_card for the same product_id defaults to (live example: search shows REDMOND KM243 sku 4668084807 while the card for that id defaults to a KM245 offer at another price). The row is SERP-faithful — reconcile it with a card by sku_id, not by the product URL.

Note rating_count counts star ratings, not written reviews; the written count is available per product via yandex_card.

price_rub is None when absent — never 0; zero results is NOT an error: the page's own "nothing found" banner makes the empty answer healthy, and meta.warnings says so.

Full field list and error codes: guide://yandex/yandex_search.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "yandex_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, 1-based.
limitNoMaximum products to return from the page.
queryYesFree-text search query in Russian, e.g. 'iphone 15' or 'стиральная машина узкая'.

Output Schema

NameRequiredDescriptionDefault
metaNo
pageNo
itemsNo
queryNo
returnedNo
page_countNo
has_next_pageNo
total_availableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.5.1

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only cover the read-only, open-world, idempotent, non-destructive safety profile; the description adds substantial behavior on top: `price_rub` is the quotable price while `price_with_plus` is conditional and `price_old_rub` must never be quoted, `price_rub` is None rather than 0 when absent, and a SERP row may describe a different family member than the card's default offer. It also discloses that zero results is not an error and that `meta.warnings` confirms it — exactly the kind of trap an agent would otherwise misread.

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 purpose and the primary price caveat are front-loaded, and the closing pointer to `guide://yandex/yandex_search` offloads the field list instead of inlining it. It runs long for a three-parameter search tool and the SERP-versus-card paragraph is the least compressed, but nearly every sentence carries a distinct distractor-prevention fact.

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?

An output schema exists, yet the description still supplies the interpretive layer the schema cannot: which price field to quote, what the alternative price means, how `rating_count` differs from written reviews, and how the row relates to `yandex_card`. Nothing an agent needs to call this correctly or report its results honestly is missing.

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%, with `query`, `page`, and `limit` all documented inline including bounds and the Russian-language expectation, so the schema already carries the parameter burden. The description adds no page/limit semantics or query syntax beyond what the schema states. 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 and resource ("Search Yandex Market and return products with both prices, ratings and sellers") and immediately scopes it against siblings by naming Wildberries and Ozon and by contrasting the SERP row with `yandex_card`. An agent can tell this apart from the other marketplace searches and from the card tool without opening any schema.

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?

Gives a clear selection rationale ("best single source for 'what does this cost right now' across the Russian market") and an explicit handoff rule: reconcile rows with `yandex_card` by `sku_id`, not by product URL. It also tells the agent that empty results are healthy rather than a failure. It stops short of naming the competing `wb_search`/`ozon_search` siblings or stating when a card lookup is the better first call, so it is clear context rather than explicit exclusions.

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