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

Annotations only say readOnly=false and idempotent=false; the description adds substantial context beyond them: a two-step flow where the person must confirm via email link within 24 hours or the slot is released, the workshop then re-confirms, and a photo of the Fahrzeugausweis is uploaded at confirmation. It also discloses the concrete return value (Buchungsnummer) and the side effect of an immediate email being sent.

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?

Front-loaded correctly: the booking action and brand scope come first, then the confirmation lifecycle, then data sources. It is one dense paragraph, though, and the inline list of services (Service, Diagnose, Reifen, Bremsen, Klima, Getriebe, MFK, Aufbereitung, Probefahrt) partially duplicates the leistungen enum in the schema, which is mild repetition.

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 20-parameter write tool with no output schema, the description covers everything an agent needs: preconditions, the confirmation/expiry lifecycle, the returned Buchungsnummer, where each vehicle field comes from, and the correct sibling for unsupported cases. No material gap remains that would cause a mis-call.

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 schema already carries the per-field definitions. The description still adds cross-parameter meaning the schema cannot: where datum/zeit must originate, which Swiss Fahrzeugausweis fields (Ziffer 23/24/36/15) map to fahrgestellnummer/typenschein/erstzulassung/kontrollschild, and that the Porsche service calculator consumes km and erstzulassung. It stops short of explaining the interaction between leistungen and beschreibung, which only the schema notes.

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?

Specific verb+resource: "Reserviert einen freien Werkstatttermin bei der Garage Kuhn AG in Thalwil" with brand scope (Porsche specialist, also VW/Audi/Skoda) and service scope enumerated. It also explicitly carves out the sibling: "Für Unfall, Lack, Einbruch, Restauration und Abschleppen gibt es offerte_anfragen." An agent can distinguish it from offerte_anfragen and termin_freie_zeiten 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?

States the hard prerequisite for the two scheduling params ("Datum und Zeit aus termin_freie_zeiten"), names the alternative tool for the excluded job types (offerte_anfragen), and points to porsche_service_berechnen's output being passed along. When-to-use, when-not-to-use, and the upstream call sequence are all explicit.

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