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

Annotations already establish the safe read-only, idempotent profile, so the bar is low, and the description adds real behavioral content: the card-expands-to-networks semantics and that closed lounges are excluded unless explicitly requested. It says nothing about ordering of results or pagination beyond the limit, which are the remaining behavioral gaps.

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-loads the returned fields, then the filtering modes, with illustrative parenthetical questions that resolve ambiguity quickly. The second sentence is long and packs four filter modes plus a card-semantics aside, which is dense but every clause carries information.

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 listing the returned fields, and it covers all five inputs either directly or via the schema. The only omission is ordering/pagination behavior for a result set capped at 100, which is minor for a read-only search.

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?

With 100% schema coverage the baseline is 3, but the description earns more by explaining that a card input expands to every lounge network it unlocks and that the query parameter spans lounge, airport, city and terminal text. This is meaning the schema does not convey on its own.

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?

Opens with a specific resource and enumerates exactly what each result carries (terminal, hours, editorial rating, access rules, page link), so the agent knows this is a filtered multi-lounge search rather than a detail fetch. It does not explicitly name the adjacent siblings (get_lounge for a single lounge, top_lounges for rankings), so the differentiation from those is left implicit.

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 selection conditions with example questions: narrow by airport, by a held card/network/status program, or by free-text words. It also correctly routes the agent to search_programs to resolve a program slug before calling. What's missing is any exclusion guidance (e.g. when to use get_lounge or top_lounges instead).

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