Side-by-side comparison: roast, body/acidity/sweetness, shared and distinct flavors, brew methods, and price difference.
| Name | Required | Description | Default |
|---|---|---|---|
| coffee_a | Yes | First coffee — id or name | |
| coffee_b | Yes | Second coffee — id or name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given that annotations already declare readOnlyHint=true and destructiveHint=false, the description adds value by detailing what the comparison covers: roast, body/acidity/sweetness, shared vs distinct flavors, brew methods, and price difference. This goes beyond the annotations to set expectations about the content returned.
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 single tightly written sentence. It front-loads the core purpose and packs the comparison dimensions into a compact list without wasted words.
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?
With no output schema, the description compensates reasonably by enumerating the comparison categories. An agent knows what kind of response to expect. It does not spell out the response format, but for a read-only comparison tool this is a minor 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?
Schema description coverage is 100%, so the schema already documents both parameters as coffee id or name. The description does not add extra parameter-level nuance, but it also does not need to because the schema carries the full burden. Baseline 3 is appropriate.
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 names a specific verb ('comparison') and resource ('coffees'), and lists concrete comparison dimensions (roast, body/acidity/sweetness, flavors, brew methods, price). This clearly distinguishes it from single-coffee tools like get_coffee and recommendation tools like get_recommendations.
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 makes the core use case clear—comparing two specific coffees side-by-side—but it does not explicitly state when not to use it or mention alternatives like find_similar or get_coffee. Usage guidance is implied rather than explicit.
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.
Each tool has a clearly distinct job: searching, fetching details, comparing, finding similar coffees, personalized recommendations, trending picks, immediate what-to-brew suggestions, and brew dial-in guidance. No two tools appear to perform the same core action.
Most tools follow a readable snake_case verb_noun pattern (compare_coffees, get_coffee, search_coffees), and the exceptions (trending_coffees, what_to_brew, find_similar) are still intuitive and consistent in style. The deviations are minor rather than chaotic.
8 tools is a well-scoped size for a specialty-coffee discovery and recommendation server. Each tool covers a different user-facing step without bloating the surface or leaving the domain feelig thin.
The tool surface covers the main coffee journey: search, inspect, compare, find similar, get personalized/or-trending/now suggestions, and brewing guidance. Minor gaps exist around enumerating available option values or filtering directly by flavor tags, but agents can work around these using search and the structured data returned.