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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, but the description adds genuinely new context: fares are recently-seen cached prices rather than live quotes, and hotel prices are excluded so the per-night figure is residual budget. That staleness caveat is exactly the kind of disclosure an agent needs before presenting results as bookable. It stops short of noting rate limits or result pagination.

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 opens with the motivating query, then lists what is returned, then closes with the two caveats that matter most. Dense but front-loaded and free of filler; the final two clauses could be tightened slightly but every sentence carries signal.

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 9-parameter tool with no output schema, the description usefully enumerates the response contents (fare, budget left per night, booking links, count of verified food spots). Only the filtering knobs – limit and direct_only – go unmentioned, which is a minor gap against an otherwise complete picture.

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?

The description clarifies the semantics of budget (total for flights plus hotel, all travellers) and how nights/travellers feed the derived per-night figure. With schema coverage at only 56%, the undocumented parameters (limit, direct_only, currency interplay with origin) get no additional explanation in the description, so it only partly compensates.

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 states a concrete verb and resource – it finds destinations whose cached round-trip fare fits a budget – and anchors it with a realistic user query ("€500, flying from Madrid, anywhere is fine"). That framing implicitly separates it from search_flights/search_hotels, which require a known destination, though no sibling is named explicitly.

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?

The quoted example conveys the intended situation (open-ended budget-first inspiration rather than a targeted search), and the month/depart_date fields hint at date flexibility. There is no explicit when-not guidance or named alternative, so selection between this and plan_trip or search_flights is left to inference.

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