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

With no annotations, the description carries the full load and does reasonably well: it states results are scheduled rather than real-time, that only change-free services are returned, the window cap (max 1440), and the default operator set (CP plus Lisbon operators). It does not say what happens when no direct service exists or whether results are capped by a page size.

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?

Front-loaded with the core purpose before examples and argument docs, and the example list efficiently conveys accepted input formats. The operator alias list is long but each entry adds usable value; minor trimming of the example set would not lose meaning.

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?

An output schema exists, so the description correctly omits return-value explanation and focuses on scope, defaults, and inputs. For a six-parameter scheduling tool the coverage is nearly sufficient, with the undocumented 'limit' parameter the main remaining hole.

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 0%, so the description must compensate; it thoroughly documents operator (ids, accepted city/region aliases, default), when (ISO, Lisbon time, default now), and window_minutes (cap 1440, default 240). However origin and destination are only implied by the example strings, and 'limit' (default 6) is never mentioned at all, leaving one of six parameters with no semantics anywhere.

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 gives a specific verb ('direct services between two stations'), a scope constraint ('no changes'), and the returned fields ('departure, arrival and duration'). The line 'Scheduled times, not live' separates it from live-vehicle siblings like transit_vehicles, and the operator examples make the domain concrete.

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 selection context: use it for point-to-point direct journeys, not for live positions or single-stop departure boards, and the 'no changes' clause implicitly routes connecting itineraries elsewhere. It also points to transit_operators for valid operator ids. It stops short of explicitly naming a sibling to use instead when changes are required.

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