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

Annotations already mark it read-only, idempotent, and non-destructive. The description adds meaningful context by disclosing deterministic scoring over Percolate's structured tasting data and the ranking criteria, so the agent knows results are stable and data-driven rather than subjective.

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?

Two concise sentences front-load the core purpose and ranking behavior without redundant details. Every clause earns its place.

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 two-parameter, read-only tool, the description covers selection, input, and output ordering sufficiently. It does not describe the exact return payload shape or error behavior for an unknown coffee id, but the schema and sibling tool set fill most of the practical gap.

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 fully documents coffee (id or name) and limit (default 5), so the baseline is 3. The description adds conceptual meaning by explaining that the coffee parameter is a reference profile and that similarity is computed from flavor/roast/body/acidity/sweetness proximity, which helps the agent choose an appropriate input.

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 exactly what the tool returns—coffees similar to a given one—and adds the ranking basis (shared flavor notes and roast/body/acidity/sweetness proximity). It is distinct from siblings like search_coffees, compare_coffees, and trending_coffees because it anchors on a single reference coffee and returns ranked similar profiles.

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 phrase 'to a given one' makes clear the intended context: the agent should use this when the user has a specific coffee and wants similar options. It does not explicitly name sibling alternatives or when-not conditions, but the usage context is unambiguous enough for tool selection.

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