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

With no annotations, the description carries the full burden, and it does add real context: the data source (Fintraffic and Trafikverket open data), the counting cadence (every night, per train), and the operational definition of on-time. It still omits permissions, rate limits, and the shape/depth of the returned aggregate, so it is useful but incomplete.

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?

A single dense sentence that front-loads the payoff (how late trains really arrive) and then lists the metrics compactly. Every clause carries information, though the metric enumeration makes it slightly long for one sentence.

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?

Since there is no output schema, the description's listing of returned metrics is valuable and mostly sufficient for interpretation. It remains incomplete about unfiltered behavior, filter combination, and result format, which an agent would need before calling it confidently.

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 25% (just the days parameter), so the description must compensate. It does clarify line, train, and country and supplies the country enum values (FI, SE), but gives no format for line id or train number and never indicates optionality or how filters interact.

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 names a specific subject (nightly train punctuality) and enumerates exactly what is reported: on-time share within 5 minutes at the last stop, median and p90 delay, and cancellations. That is far more concrete than the sibling lookups (get_line, get_station), though it does not explicitly contrast itself with 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?

It tells the agent the available filters (line id, train number, country with values FI/SE), which implies how to narrow a query, but never says when to prefer this tool, whether filters are combinable, or what happens with no filter at all. Usage is implied rather than stated.

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