Pick beers off a venue's Untappd menu that a user hasn't had

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

Adds substantial context beyond annotations: the full-menu walk across section pages, the incremental or backfill cache refresh (which explains the readOnly=false and non-idempotent hints), budget exhaustion producing another_run_needed with a resumable cache, and menu_complete=false only when the budget runs out mid-menu. It stops just short of detailing rate limits or pagination nuances, but the safety and state-mutation profile is clearly disclosed.

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 differentiation, then the mechanics, then the fallback and the username default. It is dense but nearly every clause carries operational information. Slightly long sentences keep it from being maximally crisp.

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 multi-step tool with no output schema, the description supplies the return shape (picks / not_had / had / sync plus a venue block), the unresolved-venue case, budget semantics, and resumability. An agent has enough to invoke it and to interpret the result without guessing.

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 venue, top_n, username, api_budget, and style_filter are already documented in structured fields. The description reinforces the venue-vs-menu-lines distinction and the budget's effect on menu completeness, but adds no format, syntax, or tie-breaking detail beyond the schema. 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 and resource chain: it pulls a venue's full verified menu, checks it against the user's distinct-beers cache, and ranks not-had beers by global rating. It explicitly distinguishes itself from untappd_menu_pick by input (venue instead of menu lines), so an agent can route without opening either schema.

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?

Names the alternative tool and the exact condition that selects it: a venue with no verified menu comes back unresolved, and in that case use untappd_menu_pick with the tap list. It also covers the username omission case for the caller's own account, leaving no ambiguity about when to use this versus siblings.

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