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?

Discloses a great deal beyond the annotations: not-had filtering is cache-only (no API call), ratings/styles come from a metadata cache, a beer/info call is made only on cache miss or >30-day-old metadata, capped by api_budget (~100 calls/hour), with partial:true/another_run_needed:true when the cap is hit and stale:true when refresh is deferred or fails. This tells the agent exactly how the tool behaves under load and how to react to partial results.

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?

Front-loaded with the purpose metaphor, then the concrete mechanics. Dense but each sentence carries operational information (caching, budget, partial/stale flags); the density is justified, though the multi-clause run of caching details is harder to parse than it needs to be.

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 carries return-value burden and does so for the key fields (partial, another_run_needed, stale, freshness/caveat block), noting it matches untappd_cache_not_had. The only gap is that an agent cannot see that sibling's block without opening it, but the tool's own contract is otherwise well covered.

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 coverage is 100%, so the schema already documents all five parameters with types, bounds, and defaults. The description reinforces the budget/rate-limit semantics for api_budget and the username-omission behavior, but adds little that the schema descriptions do not already carry; 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?

States a specific verb+resource: from a candidate list of beer ids, return the top N the user has NOT had, ranked by Untappd global rating, with an optional style filter. It also frames the real-world use case ('what should I order off this tap list?') and names the sibling whose freshness block it mirrors (untappd_cache_not_had), so it is distinguishable from nearby tools at a glance.

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 'what should I order off this tap list?' framing plus 'Omit username for your own account' gives clear context for when this tool applies. It references untappd_cache_not_had for the shared freshness semantics, but does not explicitly state when to prefer this over untappd_cache_not_had or search_beer, so no true exclusion guidance is present.

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