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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered and the description doesn't need to restate it. What the description does add is substantive: it enumerates the returned facets (fee, tiers, lounge programs unlocked, cards including it, count of open lounges admitting members, page link), which matters because no output schema exists. It stops short of noting behavior on an unknown slug (error vs. empty), the one remaining gap.

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?

It is a single compact sentence with no filler, and the resource type is front-loaded. However, it is a verbless noun phrase built as a long colon-delimited list, and the clause 'how many open lounges admit its members' is convoluted enough to slow parsing; a lead-in like 'Retrieve' would have cost one word and fixed the structure.

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 one-parameter lookup with a fully documented schema, this is close to complete: the description compensates for the absent output schema by describing what comes back, and annotations cover the safety semantics. It loses a point only for not clarifying the relationship to search_programs or get_points_program, which an agent working across ~60 siblings would reasonably want.

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?

There is a single parameter, ref, and the schema documents it at 100% coverage with examples ('amex-platinum, priority-pass'). The description's 'by slug' merely echoes the schema's own wording and adds no format, casing, or resolution rules, so the baseline of 3 for full schema coverage applies.

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 identifies the resource precisely — a credit card, lounge network, or airline status program retrieved by slug — and enumerates the payload (fee, tiers, unlocked lounge programs, including cards, open-lounge count, page link). The verb is elided and no sibling is named, so an agent can't tell from this alone why it should pick this over get_points_program or search_programs, but the scope of the resource itself is unambiguous.

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?

Usage is only implied: the phrase 'by slug' signals that the caller must already hold an identifier, which distinguishes it from the search/list siblings by inference rather than statement. There is no explicit when-to-use, when-not-to-use, or named alternative such as search_programs for slug discovery.

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