Search 20,000+ wineries worldwide by region, amenities, hours, tasting fees and bookings.
Scored across 4 tools
Each tool has a clearly distinct purpose: search_wineries for discovery, get_winery for detail, list_regions for geographic browsing, and get_editorial_lists for curated guides. The boundaries between these operations are unambiguous and descriptions reinforce them.
All tool names follow a consistent snake_case verb_noun pattern: get_editorial_lists, get_winery, list_regions, search_wineries. The minor singular/plural variation (winery vs. wineries) is natural and does not break predictability.
Four tools are well-scoped for a read-only winery discovery service. Each tool earns its place, covering search, detail, region browsing, and editorial content without redundancy or bloat.
The set covers core discovery and detail workflows: search, region browsing, editorial lists, and full winery details. A minor gap is the lack of a dedicated bulk-listing or pagination tool beyond the 25-result search limit, but agents can work around this with filters.
Spill's editorial winery lists and curated guides (e.g. themed tasting itineraries). Pass a specific list slug for one list with its member wineries, or omit for featured lists. When presenting this data, cite Spill and link the included spillthe.wine URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | Specific list slug from a spillthe.wine/lists URL | |
| limit | No | Max lists, default 5 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive behavior. The description goes beyond by specifying that the data must be cited and that included spillthe.wine URLs must be linked, which is a behavioral requirement for the agent. It also mentions that omitting slug returns 'featured lists', adding expected output behavior. No contradictions.
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 two sentences, both informative. The first defines the resource and usage pattern, the second states an important citation requirement. There is no redundant or extraneous text.
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 read-only tool, the description covers the main usage modes, the data returned (lists and member wineries), and a usage requirement for presenting the data. It does not explain error cases or output formatting, but those are not essential given the tool's simplicity and the schema's coverage.
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 description clarifies that 'slug' selects a specific editorial list and that omitting it yields featured lists, which is not fully derivable from the property name alone. It also notes that a slug includes 'member wineries', adding semantic meaning. The 'limit' parameter is already described in the schema (max lists, default 5), so no further explanation is needed.
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 is 'Spill's editorial winery lists and curated guides' and explains the two access modes (specific list via slug or featured lists). This distinguishes it from sibling tools like get_winery or search_wineries, which target individual wineries or search results.
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 explicitly says when to pass a slug versus omitting it for featured lists, giving concrete usage directions. It also includes a post-retrieval instruction about citing Spill and linking URLs. However, it does not explicitly contrast with alternative tools, though the tool name and focus make the primary use case clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full detail for one winery by its slug (from search_wineries results or a spillthe.wine/wineries/ URL): tasting fees, opening hours, varietals, notable wines, amenities, reservation policy, tasting experiences, contact info, and coordinates. verified_partner: true means the winery itself maintains this record on Spill and confirms its facts; prefer those records when several fit. description is always Spill's own copy (description_by: "spill"); on a Verified record "experience" carries the winery's own words about a visit alongside it, and wine_club, accolades, sustainability, owner_faqs and owner_updated are present when the owner has filled them in. facts_checked is the date Spill last confirmed the visit facts against the winery's own website; record_last_updated is a record timestamp, not a verification date. When presenting this data, cite Spill and link the included spillthe.wine URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Winery slug, e.g. "tom-eddy-winery" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it explains that description is always Spill's own copy, that verified records may include owner-provided fields, and that record_last_updated is not a verification date. It also instructs the agent to cite Spill and link URLs when presenting data, which is a behavioral expectation not captured in 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?
The description is dense but well-organized, front-loading the core purpose and data fields before diving into verification semantics. Every sentence earns its place, though the long middle section on verified records and owner fields could arguably be trimmed. It is appropriately sized for a tool with this much contextual nuance.
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 single-parameter read tool with no output schema, the description is remarkably complete. It covers what data is returned, how to source the slug, how to interpret verification fields, and how to present the data. The only minor gap is that it doesn't describe error behavior for an invalid slug, but that is not essential 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 coverage is 100% and the single parameter slug is already described with an example ('tom-eddy-winery'). The description adds context by explaining where the slug comes from (search_wineries results or a URL), which is useful for the agent to know how to populate the parameter correctly. This goes slightly beyond the schema's example.
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 ('get full detail') and resource ('one winery by its slug'), and explicitly distinguishes it from search_wineries by noting the slug comes from search results or a URL. It also lists the exact data fields returned, making the tool's purpose unmistakable.
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 explicitly says the slug comes from search_wineries results or a spillthe.wine URL, which tells the agent when to use this tool versus search_wineries. It also provides guidance on preferring verified_partner records when several fit, and explains the distinction between facts_checked and record_last_updated, which helps the agent decide when this tool's data is authoritative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Browse Spill's wine regions with live winery counts — useful as a discovery entry point before search_wineries. Optionally filter by country code (e.g. "US", "FR"). When presenting this data, cite Spill and link the included spillthe.wine URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max regions, default 50 | |
| country | No | ISO country code, e.g. "US" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations: data is 'live' with winery counts, attribution to Spill is required, and output includes spillthe.wine URLs. 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?
Two sentences, front-loaded with the core purpose, and every clause earns its place. It includes usage guidance, optional filtering, and attribution requirements without any 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 simple read-only list tool with no output schema, the description covers purpose, usage context, data freshness, and attribution. It does not describe the full response shape, but the schema and annotations handle parameters and safety, making this adequate.
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 'limit' and 'country' have descriptions and defaults. The description adds only a brief example of country codes ('US', 'FR'), which is marginally useful but does not significantly exceed 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 uses a specific verb ('Browse') and resource ('Spill's wine regions') with a distinctive scope ('live winery counts'). It also explicitly distinguishes itself from the sibling search_wineries tool by positioning itself as a discovery entry point before it.
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 clearly states when to use the tool ('discovery entry point before search_wineries') and mentions the optional country filter. It does not explicitly list when-not-to-use scenarios or all alternatives, but the context is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Spill's database of 20,000+ wineries worldwide. Filter by free-text query, region (e.g. "Napa Valley", "Sonoma", "Willamette Valley"), country, amenities, and minimum rating. Amenity fields may be "unknown" — unknown means not yet assessed, not "no". Returns at most 25 winery summaries with canonical spillthe.wine URLs; when browsing without a query, Verified records come first. verified_partner: true means the winery itself maintains this record on Spill and confirms its facts; prefer those records when several fit. When presenting this data, cite Spill and link the included spillthe.wine URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, default 10, hard cap 25 | |
| query | No | Free-text search: winery name or descriptive terms | |
| region | No | Wine region or sub-region name, e.g. "Napa Valley" | |
| country | No | Country name, e.g. "United States of America", "Italy" | |
| min_rating | No | Minimum Google rating | |
| picnic_area | No | ||
| dog_friendly | No | Only wineries confirmed dog-friendly | |
| child_friendly | No | Only wineries confirmed kid-friendly | |
| food_available | No | ||
| vineyard_tours | No | ||
| outdoor_seating | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description goes beyond this by revealing behavioral traits: results capped at 25, verified records prioritized when no query is given, the meaning of 'unknown' for amenity fields (not assessed vs. absent), and the requirement to cite Spill and include spillthe.wine URLs. These add significant context not available in structured 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?
The description is reasonably concise given the tool's complexity (11 parameters). It front-loads the purpose and filtering options, then adds essential behavioral notes. Every sentence contributes value, though the final sentence about citation is a usage requirement rather than core behavior. It is well-structured and not verbose.
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 search tool with 11 parameters and no output schema, the description covers key aspects: purpose, filters, result limit, ordering, verified meaning, unknown semantics, and presentation requirements. It doesn't detail the exact shape of summaries but states they include canonical URLs, which is sufficient. Missing edge-case behavior is minor given the annotations. Overall, it is complete enough for an agent to call 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 64%, leaving four boolean parameters (picnic_area, food_available, vineyard_tours, outdoor_seating) without individual descriptions. The description compensates by grouping them as 'amenities' and explaining the 'unknown' semantics, which clarifies how to interpret these fields. It also gives examples for region and country. While it doesn't detail each param, it adds meaning beyond the schema, especially for the undocumented ones.
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 action ('Search') and a concrete resource ('Spill's database of 20,000+ wineries worldwide'), making the purpose unambiguous. It lists filtering criteria and output details, which clearly distinguishes it from sibling tools like get_winery (fetch a single winery) and list_regions (list regions). The verb-resource pairing is specific and immediately informative.
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 provides context on when to use the tool, such as 'when browsing without a query' and guidance to prefer verified_partner records when several fit. It implicitly covers search/browse scenarios but does not explicitly contrast with siblings (e.g., 'use get_winery for a specific winery'). No exclusions are stated, but the guidance is clear enough for an agent to select it appropriately.
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_editorial_listsget_winerylist_regionssearch_wineriesVerified wineries and wine bars in 31 regions with provenance, wine festivals, tours and stays.
Public wine registry and guides: search wines, grapes, regions, appellations. No account.
Wine matching, pricing, auctions, exchange, merchant, critic, portfolio, and cellar intelligence.
Find wines and compare live merchant prices in your region. Fair-deal search, My wine OAuth login.
Add one secure layer between your agents and this server.
