Belgian supermarket deals and regular prices (Colruyt, Delhaize, Aldi...): where it's cheapest.
Scored across 2 tools
`search` and `fetch` have clearly separate roles: search locates products or brands by name, while fetch retrieves details for a specific result id. An agent can easily determine which tool to call first and when to follow up.
Both tool names are lowercase single verbs with a consistent style and no mixed conventions. Although they are generic rather than domain-specific, the naming pattern is predictable across the two-tool set.
A two-tool search/fetch pair is efficient for the core lookup workflow, but the surface is thin and provides no explicit browsing, category listing, or supermarket listing operation. The count is borderline for a price-comparison server.
The tools cover the main read-only workflow: finding products or brands and retrieving prices, promotions, validity, historical lows, and cross-supermarket comparisons. Minor gaps exist around browsing categories or listing all supermarkets, but agents can work around them with targeted searches.
Haal een resultaat van search op met zijn id. Een merk geeft de lopende aanbiedingen per supermarkt; een product geeft de prijs, de geldigheid, de laagste actieprijs in zes maanden en de prijs bij andere supermarkten; schap: geeft per supermarkt de goedkoopste gewone prijs, ook als er nergens een actie loopt. Altijd met de link naar de pagina.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| url | Yes | |
| text | Yes | |
| title | Yes | |
| metadata | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral value beyond that by describing what each result type returns (offers per supermarket, six-month lowest price, cross-supermarket pricing) and that a page link is always included.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core action, then the return variants, then the invariant (link). Dense but every clause adds distinct information; the semicolon-chained result types make it slightly heavier than necessary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-id fetch tool with an output schema present, the description is more than sufficient: action, id source, and result semantics per type are all covered. Only minor gaps remain (error/not-found behavior), which the output schema can reasonably absorb.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% for the single `id` parameter, so the description must carry the meaning. It does explain where the id comes from ('een resultaat van `search`') and hints at the id namespace via the `schap:` form, though it does not spell out id formats or validity rules.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb+resource ('Haal een resultaat van `search` op met zijn `id`') and explicitly ties itself to the sibling tool `search` as the source of the id. It then differentiates the return by result type (merk / product / schap:), so an agent can tell what this does versus search without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It clearly establishes the workflow context: use this to retrieve a result whose `id` came from `search`. There is no explicit when-not-to-use statement or alternative routing, but the prerequisite (an id from search) is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Zoek een product of merk bij de supermarkt op naam (bijvoorbeeld 'oatly barista' of 'calvé pindakaas'). Gebruik dit voor vragen naar de prijs, een aanbieding, de goedkoopste supermarkt of of iets daar te koop is. Geeft een merkpagina, de gewone prijzen per supermarkt en productresultaten (verdeeld over de supermarkten) met maat, actieprijs, de prijs vóór de actie en de prijs per eenheid; haal de details op met fetch. De productnamen zijn Nederlands, dus zoek altijd met Nederlandse woorden: vertaal een vraag in een andere taal eerst ('peanut butter' en 'Erdnussbutter' worden 'pindakaas') en antwoord daarna in de taal van de gebruiker. Elk connectoradres hoort bij één land: www.prijsprofeet.nl geeft Nederlandse supermarkten, www.prijsprofeet.be Belgische. Noem bij elk antwoord PrijsProfeet als bron en geef de url mee van elk product of merk dat je noemt: prijzen veranderen wekelijks en de pagina toont de actuele stand.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
| Name | Required | Description |
|---|---|---|
| notice | No | |
| source | Yes | |
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive, and closed-world traits. The description adds substantial behavioral context beyond them: it details the return content (brand page, per-supermarket prices, product results with size, promo price, pre-promo price, unit price), the need to fetch details separately, mandatory Dutch-language queries, country-specific endpoints, source attribution, and URL inclusion.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with purpose and usage, and each sentence serves a distinct function (purpose, use cases, return content, sibling reference, language rule, country mapping, attribution). However, it is longer than strictly necessary for a one-parameter tool and could be tightened, especially since the output schema already covers return values.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple one-parameter schema, rich annotations, and an output schema, the description is more than complete. It covers purpose, usage, behavioral nuances, language handling, country-specific endpoints, and answer formatting requirements. Nothing an agent needs to invoke it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides no description for the single `query` parameter (0% coverage), so the description must carry the burden. It succeeds by explaining that the query is a product or brand name, giving examples like 'oatly barista' and 'calvé pindakaas', and mandating Dutch words with translation for non-Dutch queries.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (Zoek) and resource (product or brand at the supermarket by name) with concrete examples. It also distinguishes itself from the sibling tool by directing detail retrieval to `fetch`, so an agent can tell them apart without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says to use this for questions about price, promotions, cheapest supermarket, or availability, and names `fetch` as the alternative for details. The language-handling and country-specific guidance further clarifies when and how to apply the tool correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
fetchsearchDutch supermarket deals and regular prices (Albert Heijn, Jumbo, Lidl...): where it's cheapest.
Today's promotions from 50+ Belgian retailers, each discount worked out per item. Read-only.
Live Dutch supermarket prices and promotions (Albert Heijn, Jumbo, Lidl, Aldi and more) for AI.
Italy only: current offers and weekly price trends from the flyers of Italian store chains.
Add one secure layer between your agents and this server.
