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.