52,000 musical instruments: prices, deals, bundles, open-box, alternatives, accessories, guides.
Scored across 7 tools
Each tool maps to a distinct resource and action (search, get, compare, list bundles/open-box/promotions, checkout), so boundaries are mostly clear. Minor overlap exists between compare_products and get_product, which already embeds alternatives and spec comparisons, but the descriptions explicitly steer the agent between them.
All seven tools follow a clean snake_case verb_noun pattern (search_products, get_product, create_checkout, list_bundles). Verbs are consistent and predictable across read and write operations.
Seven tools is well-scoped for a product catalog plus checkout server, with no redundant entries. Every tool covers a genuinely distinct slice of the storefront (search, detail, comparison, bundles, promotions, open-box, purchase).
The catalog side is thorough: discovery, detail with alternatives/accessories, comparison, bundles, deals, and checkout are all covered. The main gap is post-purchase and cart coverage — there is no way to retrieve an order, check payment status, or manage a basket, which limits the checkout flow to a fire-and-forget action.
Compare 2 to 4 products side by side - price, stock, specs, who each one suits - together with the stored spec-based comparisons between them, or pass ONE product_id with with_alternatives=true to put it next to the in-stock alternatives its buying guide compares it with. Good for "X or Y?", "what is the difference between..." and "is there something similar but..." questions. Records carry specs and short_description (get_product has the full description and the accessories). comparisons[] is written from the point of view of product_id against the alternative; two products with no stored comparison between them have none - compare their specs directly. Buying-guide text is Romanian for language=ro and English otherwise.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Locale for text + pricing (ro=RON, hu=HUF, de/en=EUR). Default ro. | |
| product_ids | Yes | Catalog product ids: 2 to 4, or exactly 1 together with with_alternatives=true. | |
| with_alternatives | No | With exactly one product id: add the in-stock alternatives its buying guide compares it with (up to 3). Default false. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations carry readOnlyHint and openWorldHint, but the description adds valuable behavioral detail: comparisons[] is written from product_id's point of view, products without a stored comparison have none, and buying-guide text is Romanian for language=ro and English otherwise. This goes well beyond what annotations and the schema alone convey.
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 dense but every clause earns its place: core capability, use cases, alternative mode, sibling differentiation, comparison directionality, and language behavior. It is longer than ideal, but the content is high-signal and front-loaded with the primary action and scope.
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 3-parameter read-only tool with no output schema, the description covers the essential context: parameter cardinality constraints, alternative mode semantics, comparison directionality, missing-comparison behavior, language behavior, and how it differs from get_product. An agent has enough to select and 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?
The schema already documents all parameters with 100% coverage, so the baseline is 3. The description adds meaning by explaining the relationship between product_ids and with_alternatives, the 2-to-4 vs exactly-1 constraint, and the language-dependent behavior of the buying-guide text, which the schema only partially hints at.
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 names a specific verb and resource ('Compare 2 to 4 products side by side') and details the exact kinds of data compared: price, stock, specs, and suitability. It also distinguishes itself from get_product by explicitly noting where the full description and accessories live, so an agent can tell the tools apart.
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 gives concrete example questions the tool is good for ('X or Y?', 'what is the difference between...'), states the alternative-mode requirement (one product_id with with_alternatives=true), and names get_product as the tool that has the full description and accessories. This is explicit when-to-use guidance with an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create an order and get a Stripe payment link the customer opens to pay. Requires authentication (send a valid X-Api-Key header). Shipping to RO, HU or DE only. Prices include VAT and match get_product for the same destination.
| Name | Required | Description | Default |
|---|---|---|---|
| buyer | Yes | ||
| items | Yes | Products to buy. | |
| expected_total | No | Optional. If set, the call is rejected when the live total moved more than 2%. | |
| shipping_address | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses a real side effect: it creates an order and generates a payment link. It also adds operational context: authentication header requirement, supported shipping destinations, and VAT-inclusive pricing consistency with get_product.
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?
Three sentences deliver the action, the auth requirement, shipping constraints, and pricing behavior with no filler. The main purpose is front-loaded, and every sentence adds decision-relevant information.
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 write operation with nested objects and no output schema, the description covers the essential behavioral context: what is created, what the customer receives, auth expectations, and shipping limitations. It does not spell out the exact response field for the payment link, but the description and schema together give enough to invoke the tool.
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 50%, and the description only indirectly covers parameter meaning by confirming prices/VAT and shipping country limits. It adds useful context for expected_total via the get_product price match, but it does not explain buyer or shipping_address semantics 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 opens with a specific verb and resource: 'Create an order and get a Stripe payment link.' It clearly states the outcome and is distinct from the read/list/search sibling tools, so an agent can identify this as the checkout-creation action without needing to inspect 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?
The description gives concrete preconditions and exclusions: authentication via X-Api-Key is required, shipping is limited to RO/HU/DE, and prices match get_product. It does not name an alternative tool, but among the siblings there is no other create/checkout tool, and the country restriction effectively tells the agent when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full details for one product by id, including description, specs, stock and VAT-included localized price. When the product is NOT in stock the record carries substitutes[]: up to 5 in-stock products of the same kind in the same price band (the same alternatives the product page shows), each as a brief record with its own product_id, price and product_url - offer them instead of searching. Every record also carries companions[]: up to 8 in-stock accessories used together with this product, one per role (role is a short label such as stand, cable, strings, case; other = no specific role) - the list our add-to-cart box shows, chosen from what customers buy together and checked with AI - each as a brief record with its own product_id, price and product_url; when the customer asks what else they need or decides to buy, offer these first (empty = we have no accessory list). Products with a stored buying guide also carry buying_guide: who the product suits (audience.levels are fixed English tokens: beginner, intermediate, professional, child, teacher, gift), typical use cases, plain-language explanations of terms, questions and answers (the last one, when present, lists the accessories of companions[]), and - while the product is in stock - a spec-based comparison with up to 3 in-stock alternatives (each with its own product_id, price and product_url). The guide is Romanian for language=ro and English otherwise; it was written with AI from our product data and a sourced fact sheet. A product sold only in a set quantity (for example speakers sold only in pairs) carries sale_quantity: price is per piece, minimum_quantity / quantity_multiple give the rule, price_for_minimum_quantity is what the customer pays at least, note says it in the record language. A product with quantity prices also carries sale_quantity.quantity_prices: the price per piece from each quantity, in the record currency.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Locale for text + pricing. Default ro. | |
| product_id | Yes | Catalog product id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover the safety profile (readOnlyHint, openWorldHint), and the description goes far beyond that: it discloses conditional record shapes (substitutes[] only when out of stock, companions[] only when an accessory list exists, buying_guide only when stored, sale_quantity only for set-quantity products) and states what empty arrays mean. That is exactly the conditional-return behavior an agent cannot infer from structured fields.
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 in sentence one, and nearly every clause encodes return-field semantics that have nowhere else to live. But it is a single dense paragraph of semicolon-chained clauses covering five distinct record sections, which hurts scanability; field-by-field structure would serve the agent much better.
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 full burden of documenting return values, and it does so thoroughly across substitutes, companions, buying_guide, sale_quantity and quantity_prices. An agent has enough to call the tool and interpret every branch of the response.
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% and both parameters are documented there, so baseline is 3. The description only lightly reinforces parameter meaning by tying language=ro to Romanian guide text and 'record language'/'record currency', adding marginal value over the schema.
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 opening sentence names a specific verb and resource scoped to a single record ('Get full details for one product by id') and enumerates what those details contain. This cleanly separates it from search_products and compare_products without needing to name them.
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?
Usage context is clear ('instead of searching', 'offer these first', 'when the customer asks what else they need'), and it explicitly tells the agent to prefer returned substitutes/companions over doing another search. However, it never explicitly frames when to call get_product versus search_products at the tool-selection level, so a small gap remains.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List bundles — pre-priced sets of products sold together for less than buying the parts separately (an instrument plus the accessories normally needed with it). Each result gives the set price, what the parts would cost separately, the saving, and exactly what is included. Good for "what do I need to get started" questions, where recommending one set beats listing five separate products.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Default discount (biggest saving first). | |
| brand | No | Restrict by brand name, partial match. | |
| limit | No | Max results (default 20). | |
| query | No | Optional text match on the set or brand name. | |
| offset | No | ||
| in_stock | No | true = only sets where every included item is in stock. | |
| language | No | Locale for text + pricing (ro=RON, hu=HUF, de/en=EUR). Default ro. | |
| max_price | No | Highest acceptable price, response currency. | |
| min_price | No | Lowest acceptable price, response currency. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral detail by specifying exactly what each result contains: set price, separate part costs, savings, and included items.
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?
Three sentences, each earning its place: definition, result contents, and use case. The practical example ('instrument plus the accessories normally needed with it') adds clarity without bloat, and the most useful guidance is front-loaded.
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 list tool with nine parameters and no output schema, the description covers the core domain concept, output shape, and appropriate use case. It relies appropriately on the schema for parameter details, though it could mention default language/currency or pagination if those were non-obvious.
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 89%, so the input schema already documents most parameters well. The description adds context about bundle semantics and result contents but does not substantially clarify parameter meanings beyond what the schema 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 uses a specific verb and resource ('List bundles'), defines what a bundle is, and explicitly contrasts it with listing separate products. The 'recommending one set beats listing five separate products' line makes its purpose distinct from sibling product-search tools.
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 states when to use the tool: for 'what do I need to get started' questions where a bundle is more helpful than separate product listings. It does not explicitly name alternative tools or state when not to use it, so it falls short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List open-box / ex-display units (Romanian: "resigilat") — returned or opened stock sold cheaper, one entry per physical unit, each with its own price, condition note and product page. Quantities are small and often one-of-a-kind, so treat availability as immediate-only. These units are NOT part of the normal catalog listings.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Default discount (biggest reduction first). | |
| brand | No | Restrict by brand name, partial match. | |
| limit | No | Max results (default 20). | |
| query | No | Optional text match on product or brand name. | |
| offset | No | ||
| category | No | Restrict by category name, partial match. | |
| language | No | Locale for text + pricing (ro=RON, hu=HUF, de/en=EUR). Default ro. | |
| max_price | No | Highest acceptable price, response currency. | |
| category_id | No | Restrict to one category id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond readOnlyHint and openWorldHint annotations, the description adds useful behavioral detail: each response entry corresponds to a physical unit with its own price, condition note, and product page. It also warns that availability is immediate-only because quantities are small and often one-of-a-kind — crucial guidance the annotations do not provide.
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 adds a clear definition, per-unit output behavior, and a practical availability warning in three sentences. Every sentence earns its place, including the Romanian term which helps resolve locale ambiguity.
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?
With 9 optional parameters, no output schema, and read/open-world annotations, the description fills important gaps: it specifies the shape of returned data, emphasizes immediate-only availability, and scopes the tool away from normal catalog listings. An agent has enough context to call the 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 89%, and parameter descriptions already explain sort, brand, limit, query, offset, category, language, max_price, and category_id. The description itself does not elaborate on any parameter semantics, so it stays at the baseline rather than adding extra value.
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 names a specific verb and resource: listing open-box/ex-display units, with clarifying terms like 'resigilat' and 'returned or opened stock sold cheaper.' It also distinguishes this tool from normal catalog listings by stating these units are NOT part of the normal catalog listings.
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 gives clear context for when the tool is relevant: open-box/ex-display inventory with per-unit pricing and small quantities. It says these units are not normal catalog listings, implying search_products or similar tools are for catalog items, but it does not explicitly name an alternative tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List what is discounted at SoundCreation right now, biggest reduction first. Each result carries price (current) and price_old (before the discount). Use this rather than searching product by product when the customer asks what is on offer.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Default discount (biggest reduction first). | |
| brand | No | Restrict by brand name, partial match. | |
| limit | No | Max results (default 20). | |
| offset | No | ||
| category | No | Restrict by category name, partial match. | |
| in_stock | No | true = only items in stock now. | |
| language | No | Locale for text + pricing (ro=RON, hu=HUF, de/en=EUR). Default ro. | |
| max_price | No | Highest acceptable price, response currency. | |
| min_price | No | Lowest acceptable price, response currency. | |
| category_id | No | Restrict to one category id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context beyond that: each result carries current price and price_old, the default sort is by biggest reduction first, and the list reflects current promotions. No contradiction with annotations.
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?
Three short sentences, each earning its place: one for purpose and ordering, one for the key return fields, one for usage guidance. The most important information is front-loaded and there is no filler.
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 read-only list tool with no output schema, the description covers purpose, default ordering, return-field expectations, and when to use it. The optional parameters are well documented in the schema, so nothing an agent needs to select and invoke this tool 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?
Schema description coverage is 90%, so the schema already documents most parameters well; the description mostly repeats the default sort behavior already present in the sort parameter." It does not add meaning beyond what the schema provides, so the baseline of 3 applies.
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?
States a specific verb and resource: "List what is discounted at SoundCreation right now," with a clear ordering rule ("biggest reduction first"). It also distinguishes itself from search_products by saying "rather than searching product by product," so an agent can tell it apart from its siblings.
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?
Explicitly says when to reach for this tool: "when the customer asks what is on offer." It also names the alternative behavior to avoid (searching product by product) and points to the better tool for that case, giving the agent concrete selection guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the SoundCreation catalog by free text (brand, model, category, or keywords), by filters, or both. With a query you get relevance-ranked results; with filters only you get a sorted browse ("cheapest in-stock electric guitar under 2000"). All prices include VAT and are locale-correct. A record with sale_quantity can be bought only in that quantity (for example speakers sold only in pairs): its price is per piece - quote price_for_minimum_quantity and state the rule (sale_quantity.note). sale_quantity.quantity_prices, when present, lists cheaper prices per piece from a quantity (from_quantity, price_per_piece, percent_off).
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Default: relevance with a query, cheapest-first without one. | |
| brand | No | Restrict by brand name, partial match. | |
| limit | No | Max results (default 20). | |
| query | No | Free-text search query. Optional if you supply at least one filter. | |
| offset | No | Skip this many results, for paging through a filtered list. | |
| category | No | Restrict by category name, partial match (use when you do not know the id). | |
| in_stock | No | true = only items physically in stock and shippable now. | |
| language | No | Locale for text + pricing (ro=RON, hu=HUF, de/en=EUR). Default ro. | |
| on_promo | No | true = only items currently discounted (price_old is the pre-discount price). | |
| condition | No | new (default) = normal catalog items. open_box = individually priced used/opened units; each result is one physical unit. bundle = pre-priced sets of several products sold together for less. | |
| max_price | No | Highest acceptable price, in the response currency for the chosen language. | |
| min_price | No | Lowest acceptable price, in the response currency for the chosen language. | |
| category_id | No | Restrict to one category id. Ids come back on every result. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/openWorld annotations, the description discloses important business behavior: prices include VAT, pricing is locale-correct, and sale_quantity items can only be bought in that quantity with per-piece pricing rules. It also explains quantity_prices and the need to quote price_for_minimum_quantity.
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 search-mode behavior, then adds pricing and quantity rules. It is dense but nearly every sentence carries useful information, though the final sale_quantity sentence is somewhat compressed.
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 13-parameter search tool with no output schema, the description covers the key behavioral complexities: query versus filter modes, sorting defaults, pricing, locale, and quantity-purchase rules. It does not fully describe the shape of returned records, but the essential calling context is present.
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 adds real meaning beyond the schema by clarifying price semantics (VAT-inclusive, locale-correct) and the special purchasing rules around sale_quantity and quantity_prices.
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: searching the SoundCreation catalog by free text, filters, or both. It distinguishes the query mode from the filter-only browse mode, but it does not explicitly differentiate itself from siblings such as get_product, list_open_box, or list_promotions.
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 explains when to use a free-text query (relevance-ranked results) versus filters only (sorted browse), with a concrete example. It stops short of naming alternatives like list_promotions or list_open_box or stating when not to use this tool.
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.
compare_productscreate_checkoutget_productlist_bundleslist_open_boxlist_promotionssearch_productsGuitar pedal specs, new and used prices, price history, review scores, board checks, buying guides.
Cross-source price compare for clothing musicians designed, wore, or founded. Real listings.
4,764 products, 626 categories: sourced prices, dated price history, independent-test coverage.
Add one secure layer between your agents and this server.
