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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and determinism profile is fully covered by structured data. The description adds the legal calculation model (25/50% payout, duration-based threshold), which is useful domain context, but says nothing about the result format, rounding or currency of the computed amount.

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?

Two tightly front-loaded sentences that lead with the action and the legal basis. The trailing English gloss ('EU ferry passenger compensation calculator') largely repeats the German sentence, which is mild redundancy but not enough to hurt usability.

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 pure deterministic calculator with three fully documented required inputs and no output schema, the description is adequate on inputs and the legal rule. It omits any indication of the return value (currency, rounding, whether a zero/denial result is possible), which is the main remaining gap since no output schema exists to cover it.

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% and all three required parameters are documented in the schema itself, so the baseline is 3. The description adds only the rule that the threshold depends on planmäßiger Fahrtdauer, without giving units or syntax beyond what the schema already provides.

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 (berechnet die Entschädigung), the resource (verspätete Ankunft von Fähre oder Schiff) and the governing regulation (VO (EU) 1177/2010). The transport mode alone differentiates it from the bus/flight/train compensation siblings, so an agent can route correctly 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?

The description makes the applicability condition explicit: delayed arrival of a ferry or ship under Regulation 1177/2010, with the threshold tied to scheduled travel duration. It stops short of naming the sibling alternatives or stating when the tool does not apply, so it is clear context without full routing guidance.

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