Top-rated beers a user has NOT had, from a candidate list

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

Annotations are minimal (readOnlyHint false, openWorldHint true, etc.), so the description carries the burden. It discloses that not-had filtering uses cache only, that metadata may come from cache or a beer/info API call on miss/stale, that calls are capped by api_budget with a rate limit, that partial results may include another_run_needed, and that username omission uses the configured account. This goes well beyond annotations and is transparent.

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 concise despite covering many details. It front-loads the purpose in the first sentence, then efficiently covers caching, API budget, partial results, and caveats in a logical flow. Every sentence adds value; there is no fluff.

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?

Given the tool's complexity (5 parameters, no output schema), the description explains return behavior (top N ranked beers, partial flag, another_run_needed) and mentions a standard freshness/caveat block by referencing untappd_cache_not_had. It does not spell out exact output fields, but that is partially mitigated by the reference to a sibling's output format. Slightly more detail on the return structure would push this to a 5.

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?

Even though schema coverage is 100%, the description adds meaningful context: bids are a candidate list, style filter is case-insensitive and matches parent style, top_n defaults to 2 and max 10, api_budget defaults to 25 and is tied to a rate limit, and username can be omitted for the user's own account. This enriches the schema's bare descriptions.

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 a memorable, specific use case: 'The "what should I order off this tap list?" tool.' It then clearly states the operation: from a list of candidate beer IDs, return the top N not-yet-had beers ranked by global rating, with an optional style filter. This distinguishes it from siblings by explicitly mentioning untappd_cache_not_had and noting differences in API call behavior.

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 provides a strong usage scenario ('what should I order off this tap list?') and explains when it makes API calls versus using cache, plus the api_budget and partial-result behavior. It references the sibling untappd_cache_not_had but does not explicitly contrast when to use one over the other, so it falls short of full alternative guidance.

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