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

Beyond the readOnlyHint annotation, the description discloses that draws are independent ('repeated calls give different drinks'), the family matching is exact yet case- and diacritic-insensitive, and that an unmatched family silently falls back to the full catalogue. These behaviors are not encoded in annotations and materially influence expectations.

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 a compact paragraph where each sentence covers a distinct aspect: action, randomness, filtering, and usage versus alternatives. No filler words or redundant restatements.

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?

The tool is simple (one optional parameter, read-only), and the description covers the full behavior: selection method, return structure, filter semantics, fallback, and use cases. The absence of an output schema is mitigated by explicitly listing the returned recipe fields.

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 already describes the 'family' parameter and lists valid values plus the fallback. The description adds the case- and diacritic-insensitivity rule and clarifies that omitting the parameter yields an unrestricted pick. This is valuable but not a large increment because the schema already handles most of the documentation.

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 opens with 'Suggest one cocktail picked uniformly at random from the catalogue' and details the return payload (ingredients, measures, steps, garnish, glassware, URL, appearances), making the action and scope explicit. It also distinguishes this tool from siblings by naming alternative tools for specific 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?

The description explicitly states 'Use this only when the user wants a suggestion or inspiration with no specific drink in mind,' and gives concrete alternatives: 'For a named cocktail use get_cocktail_recipe; for "anything with gin" use find_cocktails_by_ingredient; for "what can I make from what I have" use find_makeable_cocktails.' This is textbook when/when-not guidance.

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