With the Vitalityfit MCP server, an AI assistant (e.g. Claude or ChatGPT) can look up the cheapest offers for a specific product and pack size from German online shops and pharmacies — searching by name, PZN or EAN. The server is public, read-only, free and requires no login.
Scored across 2 tools
The two tools have mostly distinct roles: search_products discovers products and pack sizes, while search_product_offers retrieves shop-level offers for a product from that search. The similar 'search_product' prefixes could cause initial confusion, but the descriptions clearly explain the dependency and different outputs.
Both tool names use snake_case with a consistent 'search_' prefix and descriptive noun phrases. The slight plural/offers difference reflects the intended distinction rather than a naming inconsistency.
Two tools is thin for a product search and price-comparison server, though the pair covers a minimal discovery-to-offer workflow. It is borderline rather than clearly wrong.
The surface covers the core workflow: search products by name/PZN/EAN and then fetch detailed offers, prices, shipping, stock and shop links. Minor gaps exist around richer product-detail retrieval or filtering, but agents can work around them for the stated price-only purpose.
List current offers (price, shipping, delivery, stock, shop link) for one product from search_products, optionally for one pack (a pack is one pack-size label as shown on the product page; it can hold several PZNs, e.g. an original and its reimports), plus the lowest price of the last 90 days. unit_price is the normalized base price (Grundpreis) of the offer: {value, per} in EUR per 1 l, per 1 kg or per piece (per = l, kg, pcs); absent when unknown. Each result carries a disclosure (affiliate links, price source) and, for medicines, a compliance_notice with the statutory German notice. Prices only, from German online shops; no medical advice.
| Name | Required | Description | Default |
|---|---|---|---|
| pack_size | No | A pack from search_products: its identity_key when it has one, else its label. A pack is one pack-size label as shown on the product page. | |
| product_key | Yes | product_key from search_products. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a safe, non-destructive read, and the description adds substantial behavioral context: return fields, 90-day lowest price, normalized unit_price format and absence semantics, affiliate/source disclosures, and medicine compliance notices. It also scopes results to German online shops and makes clear there is no medical advice.
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 purpose is front-loaded, and the remaining sentences pack necessary return, pricing, disclosure, and compliance details without repetition. Despite being dense, every clause earns its place.
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?
There is no output schema, so the description carries the burden of explaining return values and it does so adequately: price, shipping, delivery, stock, link, unit_price, disclosures, and compliance_notice. Combined with annotations covering safety, the definition is complete enough for correct invocation.
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 description coverage is 100%, so the baseline is 3. The description still adds useful domain meaning beyond the schema by explaining that a pack is a pack-size label that may contain several PZNs, such as original and reimports, and by reinforcing product_key provenance.
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 and resource: listing current offers for one product, optionally narrowed to one pack. It explicitly ties product_key back to search_products and defines what each offer contains, so an agent can distinguish it from the sibling search tool without opening the 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 prerequisite that product_key comes from search_products and explains when the optional pack_size applies. It does not explicitly state exclusions or compare against any alternative offer-listing tool, 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.
Search health products sold by German online shops and pharmacies by name, PZN or EAN. Returns product keys, pack sizes, the cheapest price and shop count. Each result carries a disclosure (affiliate links, price source) and, for medicines, a compliance_notice with the statutory German notice. Prices only, from German online shops; no medical advice.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of products (default 5, max 10). | |
| query | Yes | Product name, PZN or EAN. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint and destructiveHint=false already covering safety, the description adds meaningful context: it lists returned fields (product keys, pack sizes, cheapest price, shop count), mentions per-result disclosures (affiliate links, price source) and compliance_notice for medicines, and reinforces the 'prices only, no medical advice' scope. It stops short of noting rate limits or error behavior, but for a read-only search this is solid.
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 the core action, then layers in return contents, disclosures, and scope boundaries across a few tight sentences. Every sentence carries useful information without repetition or fluff, and the 'no medical advice' caveat is appropriately placed at the end.
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?
There is no output schema, so the description must explain return values—and it does: product keys, pack sizes, cheapest price, shop count, plus disclosure and compliance notices. Combined with safety annotations and a fully documented two-parameter schema, an agent has everything needed to invoke this tool correctly.
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 100%—both query and limit are fully documented in the schema. The description restates the query formats (name, PZN, EAN) but adds no new parameter-level detail such as syntax examples or limit defaults beyond what the schema already provides.
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 (Search) and resource (health products sold by German online shops and pharmacies) with searchable identifiers (name, PZN, EAN). It clearly distinguishes the product-level scope from the sibling offers tool only implicitly via return fields (cheapest price, shop count), without naming search_product_offers as the alternative.
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?
The description implies usage (search by name/PZN/EAN) and sets boundaries ('Prices only... no medical advice'), but it never explicitly states when to use this tool versus search_product_offers or outlines prerequisites. The guidance is implied rather than spelled out.
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.
search_product_offers1 field changedInput schema / properties / pack_size / descriptionPrevious value: -"Pack identity_key (preferred) or label from search_products."New value: +"A pack from search_products: its identity_key when it has one, else its label. A pack is one pack-size label as shown on the product page."search_product_offerssearch_products
Add one secure layer between your agents and this server.