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

Annotations already declare read-only, idempotent, open-world and non-destructive, so the safety bar is low; the description still adds hard behavioral facts: ≤15 rows and ≤120 min caps, times always returned in Europe/Berlin regardless of the offset passed, an ambiguous station name returning a disambiguation list rather than a guess, and a mandatory attribution line in the output.

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 comes first, then routing rules, then hard limits and the attribution requirement — a sensible front-load with no filler. It is, however, written in a compressed telegram style ("A line with no DEPARTURE station … — check_transit_disruption") that occasionally costs a re-read; parentheses and dashes carry a lot of load.

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 7-parameter, no-required-parameter tool with no output schema, the description covers defaults, caps, ambiguous-name handling, language-default pitfall, return-row ceiling and output obligations (attribution). Nothing an agent needs to call it correctly or interpret the result appears to be missing.

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?

With 100% schema coverage the baseline is 3, but the description adds meaning the schema does not: the `when` window is restricted to today and ≤2 h (longer belongs to get_departures), a named train type should be paired with a longer `duration_min`, and omitting `categories` is the correct default for "which trains leave". These are usage rules for parameters, not restatements.

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?

"Next trains at a German railway station: platform, delay, cancellations" gives a specific resource, the fields returned, and the scope (German rail). It then explicitly separates itself from get_departures, describe_station and check_transit_disruption, so an agent can pick it 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 states the triggering questions ("when a train, S-Bahn or ICE leaves a named station", delays, "heute Abend") and names the alternative for each exclusion: one bus/tram/U-Bahn line, non-railway stop, another day, over 2 h → get_departures; a line with no departure station → check_transit_disruption; whole-station info → describe_station. Explicit when-not plus named siblings is the top of this scale.

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