Train stops

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds value beyond them: it states the return shape (ordered stops with date and local time), that sold-out classes still work, and warns that the first stop may precede the queried station. That is meaningful behavioral context, not restatement.

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?

Purpose is front-loaded in one sentence, then parameter caveats follow. Three short sentences, none wasted, no filler.

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 an output schema present the description need not explain return values, and annotations carry the safety profile. For a single-parameter read tool, the description plus schema cover what an agent needs, including the non-obvious edge case that the first stop can precede the queried station.

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, and the schema already documents the class_id format. The description adds disambiguation the schema lacks - 'never a train number' - plus the sold-out tolerance, which genuinely improves correct invocation.

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 - 'Every station a train stops at, in order, with the date and local time at each.' It positions itself relative to the sibling mb_search_trains as the producer of the class_id, so an agent can distinguish it from search and pricing tools without opening a 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?

It gives the workflow source ('a class_id from mb_search_trains') and a useful edge-case note ('sold-out classes work too'), but never states when to prefer this over siblings like mb_train_price_calendar or why an agent would request stops. Usage is implied by the purpose rather than explicitly routed.

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