Creator product picks with daily-verified store prices and Avahit's own price history.
Scored across 3 tools
Each tool has a clearly distinct role: search_products finds products by keyword, compare_alternatives ranks substitutes for a known product id, and get_price_history reports observed price data. There is no overlap in input type or output purpose, so an agent can select correctly without hesitation.
All three names follow a strict verb_noun snake_case pattern (search_products, compare_alternatives, get_price_history) with the verb accurately reflecting the operation. No mixed conventions or vague verbs.
Three tools is on the thin side, but each maps to a genuinely different user need (discovery, substitution, price tracking), so nothing is redundant. A get_product detail tool would round it out, but the current set is defensible.
The surface covers search, comparison, and price history, yet both compare_alternatives and get_price_history require a product id that only search_products can supply, with no direct product-detail or category-listing tool for other entry paths. Agents can work around this via search, but it is a notable gap.
Given an Avahit product id, return ranked alternatives with a match percentage explaining how close each one is (same category, price distance, product type, same store).
| Name | Required | Description | Default |
|---|---|---|---|
| productId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It adds real behavioral value by disclosing the ranking factors behind the match percentage (same category, price distance, product type, same store), but it omits whether the lookup is read-only, any result-count limits, error behavior for unknown ids, or cross-store scope.
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?
A single front-loaded sentence that leads with the input, then the output, then the scoring criteria. No filler or redundant restatement of the tool name.
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, and the description does explain the return value shape (ranked alternatives plus an explanatory match percentage), so the main gap is closed. Missing only operational details such as result caps or behavior on unknown product ids.
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?
With 0% schema description coverage, the single parameter is undocumented in the schema, and the description compensates only partially by identifying it as an 'Avahit product id' (domain-qualified, not arbitrary). It adds no format, prefix, or validity details.
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: 'return ranked alternatives' for a given Avahit product id, with the notion of a match percentage. This is clearly distinct from the siblings search_products (discovery) and get_price_history (price data), though it never names them explicitly.
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 is only implied: an agent can infer it is used when it already holds a product id and wants substitutes. There is no explicit when-to-use, when-not-to-use, or routing against search_products, which also surfaces products.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given an Avahit product id, return what Avahit itself observed about its price: current price and when it was last verified against the store, the lowest and highest price seen with dates, the average, how many checks and since when. Amazon products have no history — Amazon's licence forbids keeping their prices longer than 24 hours.
| Name | Required | Description | Default |
|---|---|---|---|
| productId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does meaningfully more than restate the name: it discloses the exact data returned and a real data-governance constraint (Amazon prices are not retained beyond 24 hours due to licensing, so Amazon products return no history). It does not cover auth requirements, rate limits, or behavior on an unknown/invalid product id.
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?
One dense, front-loaded sentence that opens with the precondition and payload, then appends the Amazon limitation where it belongs. Every clause carries information, though the long comma-separated enumeration of return fields makes it heavier than it needs to be.
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 describe return values, and it does so thoroughly, including dates, average and check counts. The main remaining gap is error/edge behavior for an unknown product id, but for a single-parameter read tool this is close to complete.
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 0%, so the description must compensate for the single undocumented parameter. It does: 'productId' is defined as an Avahit product id, which is more specific than the bare 'string' type in the schema, and the Amazon note clarifies that non-Avahit ids will not produce history. Format/validation details are still absent.
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 (return/give) and resource (price history for an Avahit product id) and enumerates exactly what comes back: current price, last-verified date, low/high with dates, average, check count and start date. The scope qualifier 'what Avahit itself observed about its price' implicitly separates it from search_products and compare_alternatives, so an agent can tell what kind of tool this is 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?
Usage is only implied by the required input ('Given an Avahit product id'), and the Amazon caveat signals one case where the tool yields no history. There is no explicit statement of when to call this versus compare_alternatives or search_products, and no prerequisites are spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search creator-recommended products by keyword. Returns title, price, store domain, store rating and a link to the product page on Avahit.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, 1-20 (default 8) | |
| query | Yes | What the shopper is looking for, e.g. 'white sneakers' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden. It does helpfully enumerate the return shape (title, price, store domain, store rating, product link), which is the most valuable trait here since no output schema exists. However, it says nothing about auth requirements, rate limits, pagination beyond the limit param, or behavior when no matches are found.
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?
Two compact sentences: the first states the action and scope, the second enumerates the return fields. Nothing is padded and the most decision-relevant information (what it searches) 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 simple two-parameter read-only search with no annotations and no output schema, the description covers purpose and return fields, which is most of what an agent needs. The remaining gap is the absence of any statement about result ordering, pagination limits, or empty-result behavior.
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 both query and limit (1-20, default 8) are already documented in the schema. The description's 'by keyword' phrasing loosely maps to query but adds no syntax, matching behavior, or format detail beyond what the schema provides, so the baseline 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?
The description gives a specific verb+resource ('Search creator-recommended products by keyword') and additionally names the returned fields, so an agent knows exactly what the tool produces. It does not explicitly contrast itself with the siblings compare_alternatives or get_price_history, but the 'creator-recommended products' scope is distinct enough that confusion is unlikely.
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?
There is no when-to-use guidance, no prerequisites, and no mention of the sibling tools (compare_alternatives, get_price_history) or when to prefer them. The schema's query description ('What the shopper is looking for') implies a search context, but routing guidance is absent.
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_alternativesget_price_historysearch_productsSearch 86 US retailers — 260M+ products with real-time pricing, stock, and price history.
Price comparison across partner retailers. Read-only, 90-day history, disclosed affiliate.
AI shopping comparison — search 50M+ products, compare prices, find deals
Save products to buy later; get notified on restock, price drop, or new release.
