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

Annotations already declare readOnly/destructive/openWorld profile, so the bar is lower. The description still adds real context: results come only from the catalog, exactly one bottle is returned by default (matching limit=1), and the 'does not sell anything or link to a store' boundary preempts a plausible user misconception.

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 tight sentences: usage trigger first, then the return semantics, then the modifier flag and the non-commerce boundary. No filler, every sentence carries information an agent needs.

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, so return values need not be explained. Given the read-only, single-lookup nature and the schema's own field descriptions, the description supplies everything else needed to call this correctly: when to use it, what it returns in scope terms, and how the zero-proof flag maps to intent.

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?

Coverage is 67%: limit and zero_proof_only have schema descriptions, but the required ingredients array is undocumented in the schema. The description partly compensates by framing inputs as 'what they already have' and maps zero_proof_only to the user's no-alcohol intent, but it never explains the ingredients list format or the limit cap of 5.

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 verb+resource: it returns the single catalog bottle that unlocks the most new drinks, which is a clear and distinctive purpose. It implicitly distinguishes itself from find_cocktails_from_bottles (listing what you can make now) by focusing on the *next* bottle to add, but never names the siblings, so differentiation is inferential rather than explicit.

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?

Gives a concrete trigger: 'when the user asks which single ingredient or bottle to add to unlock the most new cocktails from what they already have,' plus a conditional for zero-proof requests. However it offers no when-not guidance or named alternatives for cases where the user wants a full list or a recipe instead.

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