Get a château profile from bordeaux.guru: appellation, classification, terroir, vineyard size, typical blend and its tasted wines.
| Name | Required | Description | Default |
|---|---|---|---|
| chateau | Yes | Château name or slug, e.g. 'chateau-lynch-bages' or 'Lynch-Bages' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden; it discloses the returned content (profile fields and tasted wines) but doesn't state output format, error behavior, or non-mutating guarantees. 'Get' implies reading, and the content list helps, but security/behavioral details remain unspoken.
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 compact sentence with a front-loaded verb and resource, followed by a tightly listed set of included data. No filler or redundant restatement of 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?
For a one-parameter, straightforward read tool, description is reasonably complete: it names the external source and lists returned data. Minor gap of not clarifying response format, but schema covers input and the profile scope is clear.
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% with an illustrative example ('chateau-lynch-bages' or 'Lynch-Bages'). Description adds no additional parameter detail, so baseline 3 is appropriate.
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?
Description specifies verb and resource: 'Get a château profile from bordeaux.guru', plus enumerates contents (appellation, classification, terroir, vineyard size, typical blend, tasted wines). This clearly distinguishes it from exclusive sibling tools like get_terroir, get_tasting_note, or get_vintage_profile.
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?
Description implies usage for broad château overview through the word 'profile' and its comprehensive content list, but it doesn't explicitly state when to use this over narrower siblings or mention any when-not-to-use conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target clearly distinct entities or actions: château, tasting note, climate, parcel, price, lieudit. A few pairs overlap—compare_climate/get_climate_season and get_tasting_note/get_bottle_tasting—but the descriptions clarify the difference well.
The naming is highly consistent: nearly all retrieval tools use the get_<noun> pattern, while compare_, lookup_, search_, and about_ represent genuinely different operation types. All names are snake_case and follow a predictable verb_noun structure.
14 tools is well-scoped for a specialized Bordeaux en primeur and terroir data server. Each tool covers a distinct data product such as tastings, climate, phenology, terroir, prices, and château profiles, without significant redundancy.
The tool set covers the primary read-only workflows: searching wines, retrieving tasting notes, exploring château/terroir data, climate comparisons, phenology, and pricing. Minor gaps exist, such as no dedicated browse/list endpoints for appellations or vintages, but these can be worked around via search and known names.