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

Annotations only declare it as a safe idempotent read; the description adds real behavioral context beyond that: out-of-service lifts are listed first, delays are live, ambiguous station names return a candidate list with a follow-up question rather than an error, and an attribution line must be shown. These are non-obvious output and interaction behaviors the agent could not infer from the structured fields.

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-loads the resource and its contents, then the triggers, then the exclusions, then the attribution note — a sensible order with no filler sentences. It is dense and somewhat longer than needed, and the trailing "Show the attribution line." sentence is a dangling instruction rather than integrated into the flow.

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?

There is no output schema, yet the description effectively describes the return payload (address, step-free status, facilities, departures with delays, alerts, parking, charging) plus the disambiguation case. For a four-parameter read tool this leaves nothing an agent needs in order to call it or interpret the result.

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 description coverage is 100%, so the schema already explains eva_no, station, language and departures in depth, including the mutual exclusivity of eva_no/station and the enum default trap. The description adds no parameter-level meaning of its own, so the baseline 3 applies.

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?

Opens with a specific verb+resource ("one German railway station") and enumerates the exact payload: address, step-free status, lifts/escalators, platforms, departures with live delays, alerts, parking, charging. It also names the sibling tools it is not (check_station_facilities, get_train_departures, get_departures), so an agent can route without opening any schema.

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?

Gives explicit positive triggers with three real sample questions ("Was gibt es am Bahnhof Köln Hbf?", "is Hannover Hbf step-free today?") and explicit exclusions mapped to the correct alternative for each (single lift → check_station_facilities, one train → get_train_departures, bus stop → get_departures). Both the when and the when-not are covered with named alternatives.

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