yandex-lavka-mcp

get_product

Look up a single Yandex Lavka product's price, size, stock, description, and nutrition by ID, slug, or Lavka link. This read-only lookup does not modify data.

Instructions

Get one product: price, size, stock, description, nutrition. Read-only.

product is an id or slug from a search result, or a Lavka link (a lavka.yandex.ru/good/... page or a shared ...?item= link).

nutrition is the КБЖУ block exactly as the product card shows it, numbers as Lavka gives them (nothing recomputed), or null when the card has none (non-food items):

per_100g: {kcal, protein, fat, carbs} per 100 g, or null.
per_portion: the same per the card's other tab, with its label ("Всё блюдо", "На упаковку", "На 50 г", ...), or null if the card has only one tab.
default_basis: the only tab ("per_100g" / "per_portion") when the card has one; null when it has both (Lavka doesn't say which one opens).
portion_grams: the portion's weight when the card states it (from the label, or the item's weight for a whole dish/pack), else null.
warning: null, or a note that per_portion doesn't follow from per_100g for that weight — Lavka's own data is wrong then; don't log it blindly.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`product`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.1.5Oct 5, 2026

addedInput schema / properties / product

Added value: +{
+  "title": "Product",
+  "type": "string"
+}

removedInput schema / properties / slug

Removed value: -{
-  "title": "Slug",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "slug"
-]New value: +[
+  "product"
+]

First observedv0.1.0Jul 25, 2026

TDQS

A4.5/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses read-only behavior and gives unusually detailed behavioral notes about the nutrition block, including null cases and a warning when Lavka's per-portion data does not follow from per-100g data.

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 first sentence is front-loaded and efficient. The nutrition section is lengthy and partly explains return values despite an output schema existing, but it is structured and every detail is useful rather than repetitive.

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, so the description need not explain return values, yet it adds enough context about parameter forms, read-only behavior, and nutrition edge cases for an agent to call the tool correctly. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for the single parameter, so the description must compensate. It does so fully by defining `product` as an id, slug, or Lavka link page/URL, which is essential information not present in the schema.

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: 'Get one product' with the exact fields returned. It clearly distinguishes this sibling tool from `search_products` by scope: one product versus a search/list operation.

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?

Explains that `product` comes from a search result, an id/slug, or a Lavka link, which gives clear context for when and how to use it. It does not explicitly name when not to use it or compare against a sibling, but the usage context is clear.

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