Skip to main content
Glama
shoper-mcp

shoper-mcp

by exelmedia

Wyszukaj produkty / Search products

search_products
Read-onlyIdempotent

Search the read-only Shoper product catalog by name, SKU, EAN, category, or producer to find paginated product details including price and stock.

Instructions

PL: Wyszukuje produkty w katalogu sklepu Shoper (tylko odczyt). Filtry łączone przez AND: fragment nazwy, kod, EAN, kategoria główna, producent. Maks. 50 wyników na stronę, paginacja przez "page". Zwraca cenę, stan, aktywność, adres. EN: Searches the Shoper store product catalog (read-only). Filters combined with AND. Paginated, max 50 per page.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
eanNoEAN (dokładnie) / exact EAN
codeNoKod produktu (dokładnie) / exact product code (SKU)
pageNoNumer strony od 1 / page number, starting at 1
limitNoLiczba wyników na stronę (1-50) / page size
queryNoFragment nazwy produktu / product name fragment
category_idNoID kategorii głównej produktu / main category id
producer_idNoID producenta / producer id

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the repeated 'read-only' claim adds little. The description does add genuine behavioral facts beyond the annotations: filters are conjunctive (AND), the page cap is 50, and the response carries price, stock, activity and address.

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

Conciseness3/5

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

The scoping sentence is front-loaded and useful, but the description is duplicated in full across Polish and English, roughly doubling length for no informational gain. Trimming the translated echo would make it materially tighter.

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?

Seven optional parameters, no output schema, and no nesting; the description compensates by naming the returned fields and stating pagination and page-size limits. That covers what an agent needs to call it correctly, though the absence of any routing hint toward siblings is a small gap.

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%, so the baseline is 3, and most description content (name fragment, code, EAN, category, producer, page) restates the schema. The one real addition is the AND-combination semantics, which the schema never states, but that is a single point of value.

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 ('Searches the Shoper store product catalog') and enumerates the filterable fields (name fragment, code, EAN, category, producer). It does not explicitly contrast itself with get_product or category_tree, so sibling differentiation must be inferred from the sibling names.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The read-only framing and the note that filters combine with AND give implied context for when this is appropriate, and pagination behaviour is stated. However there is no explicit 'use this instead of X when Y' guidance against get_product (single-item lookup) or category_tree, leaving the agent to infer the boundary.

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