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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description adds substantial behavior beyond them: a cap of 8 matches, a synthetic 'Other hotel or villa' id as the no-match fallback, full regional coverage, and an email-based alternative for uncovered regions. That is exactly the kind of fallback and limitation detail an agent cannot infer from the readOnly sidecar.

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?

Three tight sentences: purpose and scope first, return shape and downstream id second, coverage and exclusions last. No sentence is filler and the most load-bearing facts (what it finds, what it returns) are front-loaded.

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?

With no output schema, the description carries the return-value burden and does so: up to 8 results, the id field to consume, and the synthetic fallback id. Coverage boundaries and the out-of-scope regions are also spelled out, leaving nothing an agent needs before calling.

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% and the single 'query' parameter is already documented with examples ('Sandals Negril', 'Ocho Rios'). The description adds no new meaning about the query string beyond what the schema states, so the baseline 3 for a fully documented parameter 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?

The description states a specific verb and resource ('Find hotels and villas') and scopes it precisely to properties MAPL Tours drives to from Sangster International Airport (MBJ), including a coverage count (199 properties) and named regions. An agent can immediately distinguish this destination-lookup tool from get_transfer_quote or the tour siblings.

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?

It routes the agent explicitly, saying the returned id is what to pass to get_transfer_quote, and it gives a genuine when-not case (Kingston, Port Antonio and Mandeville are quoted by email instead). It stops short of stating that this lookup must precede quoting, but the workflow context is otherwise clear.

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