Rye whiskey consensus scores compiled from published reviews, with confidence bands and citations.
Scored across 2 tools
The two tools split cleanly into single-bottle lookup (get) versus ranked multi-result filtering (search), and the descriptions make that boundary explicit. Minor overlap exists because get_rye_consensus accepts a name and search_rye_consensus accepts name keywords, so an agent could occasionally pick either for a name query.
Both tools follow the same verb_noun pattern with the same object (get_rye_consensus, search_rye_consensus). The naming is fully predictable and immediately readable.
Two tools is thin in absolute terms, but the domain is a narrow read-only score lookup and the get/search split is exactly the right decomposition. Each tool clearly earns its place with no padding or redundancy.
Lookup, filtering, sorting and citation retrieval cover the core read-only workflow for a consensus aggregator. Gaps are minor — no side-by-side bottle comparison or source-listing tool — but agents can work around these via multiple searches.
Look up one rye whiskey by name (or RyeCentral review URL/handle) and return its RyeCentral Consensus Score out of 5, confidence band (Strong / Solid / Early), confidence percent, number of published sources, last-verified date, key specs and current price range, plus the citation to show the user. Always show the citation with the score.
| Name | Required | Description | Default |
|---|---|---|---|
| bottle | Yes | Bottle name, e.g. "WhistlePig 10 Year", or a ryecentral.com review URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the description adds value by disclosing the exact return payload semantics (score scale out of 5, three enumerated confidence bands, percent, source count, last-verified date, price range) and a display obligation ('Always show the citation with the score') that is not encoded anywhere in 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?
Front-loaded with the action, then the return contents, then the citation instruction in one short imperative sentence. The field enumeration is long but every listed item (score, band, confidence, sources, verified date, price) tells the agent what to surface, so little is wasted.
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 fully compensates by enumerating the return fields and their formats, including the scoring scale and the confidence-band vocabulary. Combined with annotations covering safety and a fully documented single parameter, an agent has what it needs to call and report 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% and the single parameter is well documented, so the baseline is 3. The description adds a small but real increment: it names 'handle' as an accepted input form, which the schema description only lists as 'Bottle name ... or a ryecentral.com review URL'.
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 ('Look up one rye whiskey') and enumerates what comes back (Consensus Score, confidence band/percent, source count, last-verified date, specs, price range, citation). The single-bottle framing implicitly contrasts with the search sibling, but it never names search_rye_consensus, so differentiation is inferred rather than explicit.
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 phrase 'one rye whiskey' and the accepted inputs (name, review URL, or handle) imply this is the single-bottle lookup path, with the sibling handling broader search. However, there is no explicit 'use search_rye_consensus when you don't know the exact bottle' guidance or any note about what happens when the name is ambiguous or not found.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search and rank rye whiskeys reviewed by RyeCentral. Filter by name keywords, brand, confidence band, minimum score and maximum price; sort by score (default), confidence, price or name. Returns up to 25 bottles, each with its RyeCentral Consensus Score, confidence and citation.
| Name | Required | Description | Default |
|---|---|---|---|
| band | No | Only bottles with this confidence band | |
| sort | No | ||
| brand | No | Brand or distillery, e.g. "Sagamore" | |
| limit | No | ||
| query | No | Name keywords, e.g. "barrel proof" or "Pikesville" | |
| max_price | No | Maximum lowest in-stock price in USD | |
| min_score | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds that results cap at 25 bottles and that each result carries a Consensus Score, confidence and citation. That return-shape disclosure is genuinely useful given no output schema, though it omits pagination behavior beyond the cap and any ordering guarantees.
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 dense sentence with the core action front-loaded and filters, sort, and return shape following in logical order. It is efficient, though the compound clause list makes it slightly harder to scan than a short bulleted breakdown would 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?
With 7 params, no output schema and modest schema coverage, the description does the needed work: it covers filtering, sorting, the result cap and the returned fields. The remaining gap is the absence of explicit routing to the sibling get_rye_consensus for single-bottle lookups.
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 only 57%, and the description compensates well by naming five of the filters (keywords, brand, confidence band, min score, max price) and enumerating sort options with score as the default — the default is information the schema does not provide. Only the limit parameter goes unmentioned in prose, though the 25-cap sentence covers it.
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 pair (search and rank) plus the resource (rye whiskeys reviewed by RyeCentral), which is clearly more than a restatement of the name. It never explicitly distinguishes itself from the sibling get_rye_consensus, so an agent must infer that this is the list/filter tool and that one is the single-item lookup.
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?
Lists the available filters and sort keys, which implies when the tool is useful (browsing/querying the catalog). However, it gives no when-to-use/when-not guidance and no mention of the sibling get_rye_consensus, so the choice between search and direct get is left to inference.
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.
get_rye_consensussearch_rye_consensusS-to-F tier lists for 208 product categories. Every placement cited, with barcodes.
Cited, confidence-stamped patent intelligence over US university tech-transfer out-licensing.
Consensus rankings for 75,000+ products across 2,600+ niches.
Longevity product reviews as data: dated US prices, cited sources and disclosed store links.
Add one secure layer between your agents and this server.
