Bottles with a similar flavor profile to a given bottle, ranked by shared flavor notes and body/sweetness/char proximity. Deterministic scoring over the Pour Picks structured tasting data.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 5) | |
| bottle_id | Yes | Bottle UUID or name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds context by stating the scoring is deterministic and based on 'Pour Picks structured tasting data', which is consistent with openWorldHint=false and gives the agent confidence that results are reproducible and closed-world.
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 two sentences with no wasted words. It front-loads the purpose and ranking criteria in the first sentence and adds determinism and data-source context in the second.
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 with full schema coverage, the description covers purpose, ranking logic, and determinism. The only gap is that the response shape is not described and there is no output schema, but the tool's behavior is well-specified enough for an agent to invoke it 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 description coverage is 100%, so bottle_id and limit are already fully documented. The description maps bottle_id to 'given bottle' and implies ranking order, but it does not add parameter-level details beyond what the schema provides, so it stays at the baseline.
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 clearly states what the tool does: returns bottles similar to a given bottle, ranked by shared flavor notes, body, sweetness, and char proximity. This differentiates it from sibling tools like compare_bottles (pairwise comparison) and get_recommendations (general suggestions).
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 input context is clear: pass a bottle_id to get similar bottles. However, the description does not name alternatives or state when not to use this tool, leaving the agent to infer the distinction from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes: search, get details, compare, find similar, find cheaper, recommend, suggest for tonight, and trending. However, 'find_similar' and 'find_cheaper_alternative' overlap somewhat in that both return similar bottles, though one explicitly filters by price. 'pour_tonight_suggestion' and 'get_recommendations' also both provide recommendations, but differ in input (mood/occasion vs. taste/budget).
Tool names follow a consistent verb_noun pattern: compare_bottles, find_cheaper_alternative, find_similar, get_bottle, get_recommendations, pour_tonight_suggestion, search_bottles, trending_bottles. The only minor deviation is 'pour_tonight_suggestion' which is a bit more descriptive than the others, but it still fits the pattern.
8 tools is well within the ideal 3-15 range. Each tool covers a distinct user need: searching, retrieving details, comparing, finding alternatives, getting recommendations, and seeing trends. No tool feels redundant or unnecessary.
The tool surface covers the core discovery and recommendation workflows well: search, get details, compare, find similar/cheaper, get personalized recommendations, and see trends. Minor gaps include no explicit tool for filtering by age or rating, and no way to get a list of all bottles in a category, but these are workable via search_bottles.