Match wine text to ELIDs

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

Annotations already declare readOnlyHint=true, so safety is covered. The description goes further: it states scores are ranking-only, not probabilities, that an empty list means no accepted match, and that vintages are not in the result – all crucial behavioral details an agent needs to interpret output.

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?

Three sentences with the purpose up front, then return contract and a caveat. No 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 read-only matching tool with no output schema, the description covers what the result means (empty list, 'no accepted match'), what scores represent, and how vintages are handled. It also signals return fields, making agent interpretation complete.

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 each parameter (raw, top_n, producer_id, country_code) already documented. The description adds only an example for `raw`, not new parameter semantics, so baseline 3 applies.

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 the core function with a specific verb ('Match') and resource ('free wine text... to ranked ELID base-wine identities'). The example inputs and named return fields make the tool's purpose unambiguous and distinguish it from generic search tools.

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?

Provides a direct routing instruction: 'Vintages in the text are not part of the result: pass the vintage to elid_get_wine.' This tells the agent when to hand off to a sibling. It doesn't explicitly contrast with elid_search_wines, but the 'free wine text' scope and example clarify typical use.

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