Real US store prices with shipping, daily price history and real-deal checks. Never paid rankings.
Scored across 2 tools
find_best_options discovers and ranks purchase options, while price_history analyzes the price trend of one already-identified product, so the primary jobs are separable. There is mild overlap because both surface price data and an agent may hesitate over when to use price_history versus relying on the price/checked timestamp already returned by find_best_options.
Both names are readable snake_case, but one is an imperative verb phrase (find_best_options) and the other is a noun phrase (price_history), so there is no single predictable pattern. With only two tools the inconsistency is manageable but still breaks the verb_noun convention.
Two tools is thin for an online shopping agent; the comparison-and-price-check loop is covered, but there is no product lookup, category browsing, or store info. It sits at the borderline of under-scoped rather than clearly appropriate.
The core path (find ranked options, then check whether today's price is actually low) is present, and price_history usefully consumes the product that find_best_options returns. However, there are notable gaps: no way to fetch product details or store data, no category listing despite the stated limited coverage, and no alerts or saved-product operations.
Find the best real options to buy a product, ranked only by what is best for the buyer (never by who pays). Returns store, price, shipping, when the price was checked, why each option ranks where it does, and a buy link. Works for any product sold online in the US; stores are added in more categories every week (today: fragrance and beauty). If a category is not compared yet, it says so instead of guessing.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What the user wants, in their own words. Example: "Versace Eros eau de toilette 3.4 oz under $80" or "perfume fresco para hombre menos de $60". | |
| language | No | Language for the answer (default: the language of the query). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses ranking integrity ('never by who pays'), data freshness ('when the price was checked'), return fields (store, price, shipping, buy link, ranking rationale), and a graceful degradation behavior. Since no output schema exists, this disclosure of return content is doing real work.
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, front-loaded with what the tool does and how it ranks, with coverage caveats trailing. Slightly dense in the middle sentence, but every clause — trust signal, return fields, category coverage, fallback behavior — 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?
With no output schema, the description compensates well by naming the returned fields and the failure mode for unsupported categories. Minor gaps remain, such as how many options are returned or whether results are cached vs. live, but nothing critical for correct invocation 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 100% and both parameters are documented with examples and an enum, so the schema already carries parameter meaning. The description adds no per-parameter guidance, which is acceptable at this baseline but not value-adding.
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 ('Find'), resource ('best real options to buy a product'), and the ranking principle that defines the tool ('ranked only by what is best for the buyer'). It also enumerates the return payload, so an agent knows exactly what it gets back without consulting 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 states applicability clearly ('any product sold online in the US') and, importantly, the condition under which it should not be relied on ('if a category is not compared yet, it says so instead of guessing'). It does not, however, route the agent to or away from the sibling tool price_history, which would have made the guidance complete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Daily price history of a specific product across stores: today's lowest price, the range in recent days, and whether today's price is low compared with what it actually cost before (not with a store's 'was' price).
| Name | Required | Description | Default |
|---|---|---|---|
| product | Yes | Specific product, with size if possible. Example: "Versace Eros Eau de Toilette 3.4 oz". | |
| language | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds meaningful behavioral context: it explains that the low-price comparison is against actual historical cost rather than a store's 'was' price, and it enumerates the returned components (today's lowest, recent range, low verdict). It does not specify how many days 'recent' covers or the data source granularity, but it goes beyond the annotations in useful ways.
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 a single, dense sentence that is front-loaded with the core purpose and then layers on the key semantic nuance (actual historical comparison vs. store 'was' price). Every clause earns its place, 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?
There is no output schema, so the description carries the burden of explaining return values, and it does so at a high level (today's lowest price, recent range, low-price verdict). It remains silent on the 'language' parameter, the exact lookback window, and any pagination or store coverage limits, which are minor but real gaps for a data-retrieval 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%: the 'product' parameter is well documented in the schema with an example, but 'language' has only an enum and no explanation. The description does not compensate by clarifying what 'language' controls or adding any parameter meaning 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 clearly states the resource (daily price history) and scope (a specific product across stores), and lists the outputs (today's lowest price, recent range, low-price verdict). It does not explicitly differentiate itself from the sibling find_best_options, leaving the agent to infer that this is historical data rather than current option discovery.
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 implied by phrases like 'price history' and 'whether today's price is low', suggesting a price-checking or deal-evaluation scenario. However, there is no explicit when-to-use/when-not-to-use guidance and no direct comparison to the sibling tool find_best_options.
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.
find_best_optionsprice_historyPrice history, store prices near a ZIP and in-store clearance at major US retailers.
Cross-merchant product search with real price history, comparisons, and demand signals.
Live product prices, promotions, price history and UPC/ASIN matching across 100+ U.S. retailers.
Price comparison across partner retailers. Read-only, 90-day history, disclosed affiliate.
Add one secure layer between your agents and this server.
