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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so safety is covered. The description adds value beyond that by disclosing data currency ('live delays, cancellations'), transport-mode and operator breadth (Vy, SJ Nord, Go-Ahead, Ruter, Skyss), and the richness of each result. It omits auth needs and rate limits, but the added data-quality context is meaningful.

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?

Three tight lines following a clear purpose / 'Use when:' / example structure, all front-loaded with zero filler. Every sentence and token earns its place.

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?

For a 6-param, no-output-schema tool with full annotations, the description effectively describes the return content (times, platforms, transfers, delays, cancellations) and scope, leaving little an agent must infer. Remaining gaps (no per-param detail for results/time_is) are minor.

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 67%, so the schema already documents from/to/date/time; the description's example ({"from":"Oslo S","to":"Bergen stasjon"}) only supplies sample values for the two required params. It adds no semantics for time_is or results, and given a mid-range coverage figure the baseline of 3 is appropriate.

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?

States a specific verb+resource: journeys between two places in Norway, enumerating transport modes (train, bus, tram, metro, boat) and operators, plus the return content (times, platforms, transfers, delays, cancellations). This clearly differs from the sibling no_station_departures (a departures board) and no_find_station (station lookup), though it does not name them explicitly.

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?

The 'Use when:' line gives an explicit trigger (someone travels by public transport in Norway) with a concrete example (Oslo to Bergen). It stops short of naming alternatives or stating when NOT to use it versus the departures/station siblings, so it is strong context without routing exclusions.

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