Skip to main content
Glama

Yappman Data Supermarket Price Snapshots

Daily basket prices by barcode or product id

lookup_basket_prices
Read-onlyIdempotent

Returns shelf-price snapshot values from the UK daily 212-item basket for up to 20 barcodes (EAN) or retailer product ids, one day, up to one row per retailer: price, was-price, loyalty price, unit price, pack size and stock, as posted. Loyalty prices appear in the basket rows only, not in the index values. Static snapshot days, not live, not a price comparison, not a statement of which retailer is cheaper. No name search. Aldi has no barcodes: use product ids. Wider data: see about_the_data.

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": "lookup_basket_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoDay, e.g. "2026-10-08". Omit for the latest day loaded.
eansNoBarcodes, 8, 12, 13 or 14 digits, e.g. ["5000157024671"]. Give eans, products or both.
productsNoRetailer product ids, e.g. [{"retailer": "tesco", "retailerProductId": "254656543"}].
retailersNoOnly these retailers, e.g. ["tesco", "asda"]. Omit for all four. The basket holds no barcodes for Aldi: use products for Aldi.

Output Schema

NameRequiredDescriptionDefault
dateYes
rowsYes
creditYes
notFoundYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: data is a static snapshot rather than live, at most one row per retailer, and loyalty prices appear only in basket rows and not in index values. Minor gaps remain, such as what is returned when a barcode is untracked, but the disclosed behavior goes well beyond the annotations.

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 lead sentence front-loads the resource, scope and return fields before any caveats, and every following clause carries information. It is dense and slightly run-on with stacked negations ("not live, not a price comparison, not a statement..."), but nothing is redundant filler.

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?

With an output schema present, the description need not explain return values, yet it still summarizes them briefly. It covers freshness, row cardinality, retailer coverage gaps and where to look for wider data, which is complete for a 4-parameter filtered lookup. Only edge-case behavior (unknown barcode, empty days) is left unstated.

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%, and each parameter already carries examples, digit patterns, maxItems and the Aldi/barcode caveat in the retailers field. The description restates the 20-item cap, the single-day scope and the Aldi rule, adding little beyond what the schema already conveys, so the baseline 3 applies.

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 gives a specific verb and resource ("Returns shelf-price snapshot values from the UK daily 212-item basket") and enumerates the returned fields (price, was-price, loyalty price, unit price, pack size, stock). It also scopes the operation explicitly (up to 20 barcodes/product ids, one day, up to one row per retailer), so an agent can distinguish it from get_shelf_price_index and list_basket_products without reading either schema.

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?

It names what the tool is not (not live, not a price comparison, not a cheaper-retailer verdict) and rules out name search, which implicitly routes name-based lookup elsewhere. It also gives the concrete alternative for wider context (about_the_data) and the Aldi workaround (use product ids, since Aldi has no barcodes), which the sibling list would otherwise leave ambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources