Skip to main content
Glama
Sign In

Edwin by theButler.network

by network.thebutler
OverviewDiscussionsAdmin

Search products across merchants

search_products
Read-only

Find purchasable product matches across merchants in a specified market. Use when the user wants to find or buy something: a need, a category, a budget, a gift idea, the best product of a kind, or the price of a named product. Returns normalized product entities with merchant count, price range and the cheapest current offer per product, each with a link. Each product carries a rang that says whether it matches a name suggested for the request (by you or by Edwin) or is another catalog match. Call get_offers only when the user wants the full merchant list for one product. Queries may be in any language. Use it for shopping requests about products and their prices at online merchants, whether or not the user names Edwin or theButler.network.

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>",
      "market": "<market>"
    },
    "name": "search_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many products to return.
queryYesThe product the user is looking for: product type plus key attributes (size, colour, use case), e.g. 'oled tv 65 inch'. Keep brand and model names exactly as the user wrote them. Product-type terms in German or English retrieve best; other languages are accepted.
fieldsNoRestrict the returned product fields to these. `pid`, and on search results `rang` and `grund`, are always included. Leave this out to get the full item including its image — only pass a list if you deliberately want fewer fields.
marketYesISO 3166-1 alpha-2 country code of the user's shopping market, e.g. DE, AT, NL, FR, GB, US. Infer from the user's context.
min_priceNoLower price limit in the market currency, if the user states one.
budget_maxNoUpper price limit in the market currency, if the user states one.
suggested_namesNoOptional. Up to 8 specific, real products you would recommend for this request from your own current knowledge, e.g. {"name":"WH-1000XM6","brand":"Sony","kind":"model"} or {"name":"The Hobbit","kind":"title"}. Edwin checks each one against the catalog in this market and returns the matching catalog offers with purchase links, so every product you recommend can carry a link. Names not found in the catalog are dropped. Leave out anything you are not sure exists.

Output Schema

NameRequiredDescriptionDefault
noteNoPlain-language explanation for the user. Set whenever the result is empty, and also when something about a non-empty result needs saying — for example that the ranking did not run and the order is the raw catalog order.
itemsYes
marketYesCanonical market the results are priced for.
mischungNoHow to present the ranks, read from the query: 'anker_vorne' when the user compared with something familiar, 'entdeckung_vorne' when they asked for something less obvious, 'beide' otherwise. The item order is Edwin's ranking when a ranking ran (see note). Absent when no suggested names were looked up for this call.
empty_reasonNoMachine-readable reason for an empty result. restricted_category: matches existed but fall into a product category this connector does not serve. no_match_in_market: nothing matched in this market. no_offers_for_product: the product has no merchant offer here at all. no_fresh_offers_for_product: the product has offers, but none is confirmed by the most recent import of its source, so there is no up-to-date price — do not quote an older one. query_too_short: the query carried no searchable terms. market_not_covered: no offers in this market at all. unknown_pid: no product with that id — call search_products for a real one. no_substantial_match: products matched, but none had a recognizable brand or publisher and the fields required for the product type — say so; the user can explicitly ask for unbranded or self-published items.
app_summariesNoOnly for Edwin's app view: it can load short product summaries for these results. Ignore it; nothing to show or say.
wenig_auswahlNoTrue when fewer than three products passed the checks for their product type among the matches checked (the note says whether that was all matches or only part). Say that the selection is small instead of padding the answer. Absent when part of the search did not answer in time.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description still adds substantive behavior: the normalized return shape (merchant count, price range, cheapest current offer per product, each with a link), the match-tier flag that labels results as suggested-name matches vs. other catalog matches, and the rule that suggested names absent from the catalog are silently dropped. It stops short of describing pagination, result ordering, or empty-result behavior.

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?

Front-loaded with purpose, then matching signals, return shape, and the get_offers routing rule in a sensible order; every clause is functional. Minor drag from the typo "a rang" and the closing branding sentence about Edwin/theButler.network, which largely repeats the earlier scoping point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and annotations cover the safety profile, so the description needn't explain return values in full. However, it introduces the undefined "rang" field (and the schema references "grund"), neither of which appears in the fields enum or is explained, and it says nothing about result ordering or what an empty match set looks like — a real gap for a discovery tool whose usefulness depends on interpreting match tiers.

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 query syntax, market inference, price bounds, limit, fields, and suggested_names are all fully documented in the schema itself. The description adds little parameter-level meaning beyond restating the language tip that already appears in the query schema. Baseline 3 applies when the schema does the heavy lifting.

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?

Opens with a specific verb and resource ("Find purchasable product matches across merchants in a specified market") and spells out the request shapes it serves — need, category, budget, gift idea, best-of-kind, or price of a named product. It also names the sibling it is not (get_offers) and states that boundary, so an agent can route without opening 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?

Gives explicit when-to-use triggers (user wants to find or buy something; price checks; shopping requests regardless of whether Edwin or theButler.network is named) and an explicit when-not/alternative rule: "Call get_offers only when the user wants the full merchant list for one product." Language guidance is also included, leaving little to inference.

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

All Edwin by theButler.network toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources