Spill Wineries

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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, and non-destructive nature. The description adds valuable context beyond annotations: clarifies that record_last_updated is not a fact-verification date and mandates citation/linking. No contradictions with annotations; this extra detail enriches behavioral understanding.

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, no fluff. The first sentence front-loads the purpose and data scope; the second adds necessary caveats. Every sentence serves a purpose (listing expected data, clarifying a field, and giving presentation instructions). Well-structured and efficient.

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 retrieval tool, the description is complete: it enumerates the returned fields (tasting fees, hours, varietals, etc.), clarifies a subtle data field, and includes presentation requirements. No output schema exists, but the description sufficiently sets expectations for the response content.

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 covers 100% with a clear description of the slug parameter. The description adds context on where to obtain the slug (from search_wineries results or URL), and implies the format, which goes beyond the schema's example. This adds meaningful value to parameter understanding.

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 tool fetches full detail for one winery by slug, and explicitly mentions the slug source (from search_wineries results or a spillthe.wine URL). This distinguishes it from siblings like search_wineries (search) and list_regions (regions), establishing a specific verb+resource with clear scope.

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 provides usage context by specifying the slug comes from search_wineries results or a URL, and includes citation/linking instructions when presenting data. However, it does not explicitly state when not to use this tool or name alternative tools, though context implies it is for detail retrieval after a search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only and idempotent safety, and the description adds valuable behavioral context: amenity fields may be 'unknown' (meaning not yet assessed, not 'no'), results are capped at 25, and output includes canonical URLs plus a citation requirement. This goes beyond the annotations by explaining data semantics and output constraints, though it does not detail all summary 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 description is concise and front-loaded: it opens with the main search capability, then lists filters, adds a crucial data quirk, states the result limit, and closes with a usage instruction. No unnecessary words, each sentence 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?

Given the tool's 11 parameters and lack of an output schema, the description covers essential aspects: purpose, filtering dimensions, unknown-state caveat, result cap, and citation requirement. It does not explain output summary fields or sorting/pagination beyond the cap, but the absence of these is tolerable given the tool's search nature and the presence of sibling tools that handle specific 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 description coverage is 64% (7 of 11 params have descriptions). The description adds context for the amenity boolean fields (all may be 'unknown'), which partially compensates for the four undocumented params (picnic_area, food_available, vineyard_tours, outdoor_seating). However, it does not individually explain those parameters or their semantics beyond the general 'amenities' label, so it only marginally improves on 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 description clearly states the tool searches Spill's database of 10,000+ wineries, with specific filter categories (query, region, country, amenities, min rating). It distinguishes from siblings (get_editorial_lists, get_winery, list_regions) by focusing on search across many wineries, not lists, single entries, or region 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 implies usage for finding wineries but does not explicitly mention when to prefer this tool over siblings (e.g., 'for a specific winery use get_winery'). It provides context like the 25-result cap and citation requirement, but lacks explicit exclusions or alternative recommendations, leaving usage guidance implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.