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

With no annotations, the description carries the full burden and does so thoroughly: output ordering, one-way USD fares valid in either direction, inclusive source dates, overlapping amendments both returned, null fare categories unavailable, no cross-fiscal-year fallback, tier-based date limits, and data freshness ('latest imported table, not past publication snapshots'). It also discloses that these are eligible contract prices, not live availability, and that caching means newly imported data needs X-Bypass-Cache: 1.

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?

The core action is stated in the first content sentence and nearly every subsequent sentence adds a genuine caveat (fees, tiers, caching, freshness). It is dense and slightly over-long — the external links and full curl example could be trimmed — and the opening bare fragment 'City Pair contract airfares' delays the actual verb.

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 read-only lookup with no annotations and no output schema, the description covers behavior, data provenance, pricing caveats, and access-tier limits well, but defers result field details to an external '200 response example' and does not say what an empty match set looks like.

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 origin/destination/date/verification_url are already documented, and the description largely restates the code-pair semantics. It adds only the 'today by default' date behavior and tier-dependent date ranges beyond the schema, which is a marginal increment over the baseline for fully described parameters.

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: returns GSA City Pair contract award airfares for an airport/city code pair and date. It is clearly distinguishable from siblings like get_city_pair_locations (location lookup) or get_gsa_perdiem_by_destination (per diem rates).

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 explicit access-tier conditions (Sandbox/Google add-on = today only; Pro = current fiscal year; Business = any loaded fiscal year), states there is no fallback to other dates/fiscal years, and says to book through the agency's authorized system. It stops short of routing the agent to a specific sibling (e.g., get_city_pair_locations) when the code itself is unknown.

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