Sync a user's wishlist into the cache

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

Annotation coverage is thin on the details that matter here (readOnlyHint=false and idempotentHint=false only signal that cache writes occur), and the description fills the gap: full-pass semantics, ~25 beers per call, deletion of de-wishlisted beers only after a complete pass, per-page resumability, and rate-limit handling with a documented stop reason and resume_at. The only mild tension is destructiveHint=false versus post-pass cache deletions, but those are scoped cache maintenance rather than user-data destruction, so it reads as clarification rather than contradiction.

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 core action and purpose, then layered with operational detail in a logical order. It is dense and long for a two-parameter tool, but nearly every clause carries behavioral information an agent cannot get from the schema or annotations.

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?

There is no output schema, so the description compensates by naming the key return signals (another_run_needed, stopped_for_rate_limit, rate_limit.resume_at) that drive correct looping and retry decisions. Nothing essential for correct invocation or follow-up behavior is missing.

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 both parameters (username, max_pages) are already documented with defaults and bounds, making 3 the baseline. The description adds useful pagination context (~25 beers per page, small wishlists) and the self-vs-other username rule, but does not explain default or maximum page counts beyond what the schema already says.

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 and resource ("Mirror a user's Untappd wishlist (user/wishlist) into the local cache") and names the endpoint it reads from. It explicitly distinguishes itself from untappd_wishlist_add / _remove, which is the nearest confusing sibling, and from untappd_user_wishlist by being a cache-population rather than a read.

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?

Gives concrete when/when-not guidance: run it so pick tools can boost wishlisted beers without an API call, re-run until another_run_needed is false, and use the add/remove tools instead for actually changing the wishlist. It also states the precondition for another user's wishlist (public account or friendship) and the username-omission case.

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