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

With no annotations provided, the description carries the full burden and succeeds unusually well. It discloses the live-vs-timetable data caveat ('Live positions only where operators publish them; boats are timetables'), the no-key requirement, the coverage limits, and the exact shape of the return payload — exactly the behavioral traits an agent needs that the schema cannot convey.

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?

Roughly 130 words, but every clause earns its place: audience first, then query format with examples, output contract, coverage boundary, and caveats. The return specification is grouped logically (boat vs bus/tram/monorail) and the 'No key' note resolves the most common agent question in two words.

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?

Given there is no output schema, the description functions as the entire return contract, enumerating per-mode fields and both URLs. It also covers the three things an agent cannot infer from schema or annotations — geographic scope, data freshness behavior, and authentication — making it complete enough to invoke correctly on a first try.

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 only 50%, so the description must compensate — and it does for 'q' by supplying six varied examples (Miyajima, 宮島, Naoshima ferry, Shirakawa-go bus) and clarifying that mode words like next/ferry/bus are acceptable. The 'lang' parameter is not addressed in the description, but its enum values and default are self-documenting in the schema, so the gap is minor.

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 uses a specific verb ('Returns') with a clearly named resource — next boat/bus/tram/monorail departures from a place in Japan — and enumerates the exact output fields (time, minutes to go, operator, route, stop number, URLs). The scope is sharply defined by region list and place count, which is enough to distinguish it from siblings like 'place' or 'rtk_bases_near' even without explicitly naming them.

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?

Clear context is set: 'For travellers in Japan', with concrete query examples and an explicit coverage boundary (six regions, 26 places, validity through 2026-09) that lets an agent infer whether a location is supported. It stops short of naming alternatives or stating when-not-to-use, but the audience and scope are specific enough to route selection correctly.

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