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

Annotations already declare readOnly/openWorld/non-destructive, so safety is covered; the description usefully adds that results carry departure times, operator, pier/pickup, per-person or per-vehicle pricing, and a boat photo page, and it discloses that 12Go (a third party) handles booking and payment for non-partner routes. It stops short of stating pagination, coverage gaps, or what happens when no route exists, so it adds context without a complete behavioral picture.

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 purpose is front-loaded in the first clause, but the body is a single dense run-on packed with a long island list, an ellipsis, and a parenthesized clause nested inside another parenthetical. Significant trimming is possible without losing selecting 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?

With no output schema, describing the returned fields (times, operator, pier, price, photo) is genuinely necessary and is done. All six parameters are schema-documented and the booking hand-off is explained; only edge-case behavior (no results, notice window failure) is left implicit.

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 the baseline is 3. The description contributes little beyond the schema: it names example places and mentions per-person vs per-vehicle pricing, but never explains the type filter (and its prose mentions catamarans, vans and taxis while the enum only accepts Ferry/Speedboat), nor what date or passengers actually change.

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 opening sentence names the resource and scope precisely ('Transfers across the whole of Thailand') and enumerates the transport modes covered, which clearly separates it from search_flights and search_hotels. It never uses an explicit verb like 'search' or 'list', relying on the tool name for that, but the domain 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?

It gives a concrete downstream routing rule that most tools lack: Phi Phi Paradise routes (with a trip_id) go to book_transfer, while everything else is an external 12Go listing with its own booking link. That tells the agent what to do after the search, but there is no explicit statement of when to prefer this over siblings like search_experiences or check_availability.

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