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

Annotations already establish readOnlyHint, idempotentHint, and non-destructive behavior, and the description adds meaningful context beyond that: it discloses compact result contents, live Shopify price and availability, partial taste-note returns, food_pairing nullability, and the meaning of default_variant_id and default_size. It also clarifies that type "sparkling" includes Champagne and that price filters omit wines without verified current prices.

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 front-loaded with purpose and filter behavior, and every sentence contributes some operational detail. It is dense and long, but that density is justified by the 12-parameter surface area and the need to route agents away from inappropriate sibling tools.

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?

An output schema exists, yet the description still usefully summarizes return shape and the semantics of default_variant_id and default_size. Combined with the explicit sibling routing and filter behavior, the definition gives an agent everything needed to invoke search_wines 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 description coverage is 100%, so the schema already documents every parameter thoroughly. The description still adds cross-parameter guidance by explaining what query does and does not match, and by directing style, budget, and food matching to the appropriate filters. This is useful but largely reinforces schema-level information.

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: searches the NEVINI wine catalog by free text and filters, then enumerates the filter dimensions. It also distinguishes itself from siblings by naming get_wine, get_catalog_overview, and get_store_info for their respective use cases.

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?

Explicitly explains when to use query versus filters, including that query does not match taste, food, or budget words and that those should use the dedicated filters, food, and sort. It also routes the agent to get_wine for other bottle sizes, all taste notes, and full descriptions, and to get_catalog_overview and get_store_info for complementary needs.

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