Porsche Service Calculator (Garage Kuhn)

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 profile is covered. The description adds value beyond that by disclosing the return content in detail - the complete plan with all work per service plus Zusatzwartung, original Porsche wording, page number and source - which matters given there is no output schema.

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?

The purpose is front-loaded, but the same content is stated twice, once in German and once in English, which effectively doubles the length without adding meaning. It is not fatally bloated, but the bilingual duplication is not fully earning 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 one-parameter fetch tool with annotations that cover the safety profile and no output schema, the description supplies the necessary return-content details (full plan vs. calculation, source and page references). It is complete enough to call correctly, with only minor room for authentication or retrieval-behavior notes.

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 the single parameter 'id' is documented in the schema as 'id aus search', so the baseline is 3. The description reinforces that the id identifies a search hit but adds no format, type, or sourcing detail beyond the schema.

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: it retrieves ('Ruft ... ab') one hit from search, returning either a full Porsche maintenance plan or a calculation. It ties itself to the sibling 'search' as the source and names what the fetched object contains, so an agent can distinguish it from search or the other porsche_* tools. It does not explicitly contrast with porsche_wartungsplaene, keeping it short of a 5.

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 phrase 'einen Treffer aus search ab' implies the intended workflow (call search first, then fetch a specific hit by id), which is decent implied usage. However there is no explicit when-to-use statement, no when-not, and no direct comparison to the sibling alternative 'search' or 'porsche_wartungsplaene'.

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

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

Beyond the annotations, the description explains the full post-submission workflow: no appointment, response within one business day, email confirmation link, document and photo upload, address completion, terms acceptance, and deletion after 24 hours without confirmation. These are important behavioral traits for an agent to understand before invoking the tool.

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?

The description is long, but the complexity of the tool (22 parameters, document upload, confirmation flow) justifies most of the detail. It is front-loaded with the core action and services, though the final English summary is somewhat redundant.

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 complex mutation tool with no output schema, the description covers the key workflow, required user confirmation, document upload, and cleanup behavior. It does not describe what the tool itself returns to the caller, and it does not discuss duplicate or idempotency behavior, leaving minor completeness gaps.

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%, so the schema already defines all 22 parameters. The description still adds useful meaning by tying vehicle fields to the Swiss Fahrzeugausweis (Ziffer 23, 24, 36, 15) and by noting that role, insurer, and claim number are helpful for accident cases. It does not explain every parameter, but it compensates where the workflow context matters.

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 states a specific verb and resource: creates a quotation request at Garage Kuhn AG in Thalwil for five named service categories. It also distinguishes the action from appointment booking by saying 'Ohne Termin', which helps separate it from the sibling termin_buchen tool.

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 gives clear usage context (accident, paint, break-in, towing, restoration) and a when-not condition: if the vehicle is not drivable or has broken down, call first instead. It does not explicitly name sibling alternatives such as termin_buchen, so it falls short of full alternative routing.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds valuable behavioral context beyond annotations: it details returned content (next service timing/mileage, Porsche's wording with page link, following services, Garage Kuhn booking link with vehicle data, reminder with date/text/calendar file) and includes a disclaimer ('Richtwert ohne Gewähr').

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?

The description is front-loaded with the core purpose, but it is long, bilingual, and somewhat redundant: the English sentence repeats a subset of the German output details and omits several specifics. Parameter guidance and disclaimer are interleaved, reducing structural clarity for a complex tool.

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?

No output schema exists, so the description must explain return values; it does so in detail, covering next service, maintenance scope, links, and reminder contents. With 100% schema coverage for parameters and annotations covering safety, the remaining gap is minor: it does not clarify how this tool relates to sibling porsche_service_erinnerung or whether it creates a reminder versus merely including reminder data.

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%, so all nine parameters are already documented with examples, enums, and constraints. The description only restates the alternative car specification modes ('modell', 'baureihe', 'plan_id') without adding syntax, format, or interaction rules beyond the schema.

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' / 'Calculates') and resource (Porsche service due next), including output scope: next service timing/mileage, tasks in Porsche wording, booking link, reminder. It distinguishes itself from a simple plan lister by describing computed results, though it does not explicitly name sibling tools like porsche_wartungsplaene as alternatives.

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?

Provides parameter input modes (modell, baureihe, plan_id) but no when-to-use guidance, prerequisites, or explicit comparison to sibling tools such as porsche_wartungsplaene or porsche_service_erinnerung. An agent must infer that this tool is for calculating a service schedule rather than fetching plans or managing reminders.

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

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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior, so the description is not required to restate safety. It adds meaningful behavioral detail: the reminder date is computed four weeks before the next service, at latest one year for the annual service, and the output includes a calendar file with an alarm the day before at 9 AM. It does not describe error handling or edge cases, but the core behavior is well disclosed.

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?

The description is front-loaded with the main purpose and output details, so an agent can quickly understand the tool. It is somewhat redundant because the final English sentence repeats the core purpose already stated in German, but the structure remains efficient overall.

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?

Given nine parameters, no output schema, and rich annotations, the description does a good job of explaining what is returned: date, title, text, booking link, and calendar file. It also explains the date calculation rule. It does not resolve the complex relationship among modell, plan_id, baureihe, and variante, but the schema descriptions cover those parameters.

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%, so the schema already documents all nine parameters thoroughly, including enums, formats, and constraints. The description adds no parameter-level meaning beyond that, so the baseline score 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?

The description states a specific verb and resource: it returns a service reminder for a Porsche, including concrete outputs such as date, title, text, booking link, and an .ics calendar file. It references the sibling porsche_service_berechnen, but does not clearly explain why an agent should choose this tool over that sibling beyond mentioning reminders and maintenance planning.

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 phrase 'Für Erinnerungen und die Planung von Wartungen' gives an implied usage context, but there is no explicit when-to-use or when-not-to-use guidance relative to porsche_service_berechnen or the other siblings. The comparison to porsche_service_berechnen is ambiguous because it says 'same details' rather than distinguishing the use case.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered structurally. The description adds useful context by listing what the plan records contain and tying the data to the service calculator, but discloses nothing about result size, ordering, or completeness.

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 with the core purpose and the field list, and the optional filter is stated last. It is somewhat padded by a German/English duplication that restates the same fact and repeats "Garage Kuhn", but the size is still reasonable.

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?

With no output schema, the description compensates well by enumerating the returned fields. For a single-optional-parameter read tool whose annotations carry the safety profile, this is nearly complete; only sorting/pagination expectations are unaddressed.

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% and the single parameter (baureihe) is documented with an enum in the schema. The description only restates that filtering by Baureihe is optional, adding no syntax or semantics beyond the schema. Baseline 3 applies.

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 states a specific verb ("Listet") plus resource ("Porsche-Wartungspläne") and enumerates the returned fields (Plan-ID, Baureihen, Zeitraum, Herausgeber, Generation, Varianten). It clearly identifies this as a reference-data lookup for the Garage Kuhn service calculator, but does not explicitly distinguish it from siblings like search or porsche_service_berechnen.

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?

Usage is only implied: it surfaces the maintenance plans behind the service calculator, and notes the filter is optional. There is no explicit when-to-use or when-to-prefer-a-sibling (e.g. porsche_service_berechnen) guidance.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful behavior beyond that: search returns a pre-computed result when the query contains km and first registration, and only hits are returned so fetch is required for full text.

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 with the verb and resource, then workflow guidance; every sentence carries information. The German content is restated almost verbatim in English, which is deliberate for bilingual users but is still duplication that costs some tightness.

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 single-parameter, annotation-rich search tool with no output schema, the description covers input format, special input behavior, and the follow-up fetch step. It stops short of describing the hit list shape or result limits, a minor gap.

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?

Only one parameter with 100% schema coverage, so the baseline is 3. The description adds real meaning by showing a richer example query ('997 Carrera, 96000 km, 03.2009') and explaining that embedding mileage and a date changes the result type, which the schema description does not convey.

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 and resource ('Sucht Porsche-Wartungspläne ... nach Modell oder Baureihe') with concrete query examples, and notes that a ready calculation is returned when mileage and first registration are present. It routes the agent to fetch for full text, though it does not contrast with the sibling porsche_wartungsplaene or porsche_service_berechnen 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?

Gives clear usage context: search by model/series, and include km plus first registration to get the finished calculation first. It also states the retrieval step ('Treffer mit fetch abrufen'), establishing the search-then-fetch workflow. No explicit when-not-to-use or named alternatives among the other siblings.

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

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.

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

Annotations already cover readOnly, idempotent and non-destructive, so the bar is lower; the description still adds real context: the 07:30-12:00 / 13:00-18:30 weekday availability, exclusion of holidays and company holidays, the three-week horizon, and that results also include services bookable by appointment vs. by quote.

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?

The availability scope and constraints are front-loaded in the first two sentences before the optional-filter note. The remaining text—brand history and the English restatement—is padding that does not help an agent decide or call, so this is the weakest part of an otherwise tight description.

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?

No output schema exists, and the description does step in to say the response includes both appointment-bookable and quote-only services, plus the bookable window and slot length. That is enough to call it correctly; only the exact result structure remains unspecified.

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% with explicit date-format and enum descriptions, so the schema does the heavy lifting. The sentence 'Optional nach Zeitraum und Tageszeit eingrenzen' only restates what von/bis/tageszeit already convey, adding no new syntax or constraint detail.

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 and resource ('Liefert die freien Termine'), plus concrete scope: 30-minute intake slots at Garage Kuhn AG in Thalwil. An agent can tell this is the availability-lookup tool as distinct from termin_buchen, though no sibling is named 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?

Says the result can optionally be narrowed by time range and time of day, which implies when to pass filters, and gives a bookable window (tomorrow to three weeks out). It never says when not to use it or that booking should follow via termin_buchen, so routing is left to inference.

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