Schitterhof CAMPING WEISS

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

Annotations already mark this as non-read-only, open-world, non-idempotent, and non-destructive. The description adds substantial behavioral context beyond that: the hold period, the shorter hold and instant-payment rule for near-term events, the fact that the reservation becomes binding only after payment, and the no-invented-personal-data rule.

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 and the prerequisites are clearly numbered. It is somewhat long, especially the example confirmation wording and the bilingual closing sentence, but the length is largely justified by the legal and voice-booking constraints.

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 14-parameter mutation with no output schema, the description covers the critical invocation context: prerequisites, consent, hold behavior, payment binding, date constraints, and personal-data handling. It does not describe the return value or failure behavior, which is a minor remaining 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?

Schema coverage is high at 86%, so the schema already documents most parameters. The description still adds useful meaning for key fields: terms_accepted is gated on explicit guest consent, email is the guest's own address for the payment link, and dates must be ISO within the event window.

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: reserve a pitch, e-mail the payment link, and complete the booking by voice. It is clearly distinguishable from siblings because it names get_availability as a prerequisite and describes the reservation action itself.

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 explicit ONLY-call-after conditions: get_availability must show the category is free, the guest must be told the total price and asked one confirmation question, and the guest must explicitly agree and provide name and e-mail. It also ties terms_accepted to that explicit consent, leaving little to inference.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower and the description still adds real context: the four availability states, that max vehicle length and persons are returned, and the non-obvious caveat that included_adults varies by event and category. It stops short of saying whether prices are per night, what currency, or how large a response can get.

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 first sentence front-loads purpose and the enumerated states; the second delivers the included_adults caveat, which is the highest-value detail. The appended German restatement duplicates the same content without adding information, costing some efficiency.

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?

There is no output schema, so the description must carry the return-value burden, and it does list the states and the key fields (from-price, included_adults, max vehicle length, persons). Missing details such as currency, price period, and response shape for multiple categories keep it from being fully complete.

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 event_slug (sourced from list_events) and the optional category_key are already documented in the schema. The description adds no further semantics for category_key — it does not say whether omitting it returns all categories or how filtering changes the response — so 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 names a specific verb plus resource (availability and from-prices per pitch category for one event) and enumerates the four possible states, so an agent knows exactly what comes back. It never names the adjoining sibling get_price_estimate, which occupies nearby territory (pricing), so the boundary is inferable rather than stated.

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: you call it for one event to see category-level availability and starting prices. There is no explicit when-to-use/when-not guidance and no route to alternatives such as get_price_estimate for an exact quote or create_reservation for booking.

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 and destructiveHint=false, so the safety profile is covered. The description adds useful context that the returned link is the guest-facing self-booking path rather than an internal booking action. It says nothing about link lifetime, whether the URL is pre-filled from the optional parameters, or whether it is per-category or per-request.

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?

Very short and front-loaded with the core fact (the URL), followed by the alternative. The full German restatement is redundant for an agent that already parsed the English sentence, which costs it the top score, but total length is still minimal.

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 correctly explains what is returned (a URL), but three of five parameters are undocumented and it is silent on whether the optional parameters shape the link. For a tool whose main misuse risk is passing adult/child/night values that silently do nothing, this leaves a significant 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?

Schema description coverage is 0% across five parameters, so the description carries the full burden and fails to explain adults, children and nights – the agent cannot tell whether these prefill the booking link or filter availability. Only category_key is obliquely hinted at by 'this category'.

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 the concrete artifact returned: 'The URL where the guest books this category on the website', which lets an agent distinguish it from the other siblings. It is a noun phrase rather than verb+resource, but the intent (retrieve a self-service booking URL) is unambiguous.

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 names one alternative, create_reservation, but never states the condition that selects between them – the agent must infer 'use this when the guest should book themselves rather than have the agent create the reservation'. No guidance on interaction with get_availability/get_price_estimate, which normally precede a booking decision.

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, closed-world and non-destructive, so the safety profile is covered. The description contributes the one thing annotations cannot: that the tier deadlines are measured from event start rather than booking date, which affects how returned data must be interpreted. It says nothing about the shape of the returned policy (percentages, deadlines, currency) — acceptable since no output schema exists but a gap nonetheless.

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?

Extremely short, but not front-loaded with a purpose statement — it opens with a bare noun phrase. Roughly half the text is a German mirror translation that adds no information for an agent and duplicates the English clause.

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 tool with no output schema and 0% parameter coverage, the description is too thin: it neither describes the returned tier structure nor explains the required event_slug. The reference-point detail is useful but leaves most of what an agent needs 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 description coverage is 0% for the single required parameter event_slug, so the description carries the full burden and provides nothing — no format, no examples, no distinction from an event ID. Only the parameter's self-explanatory name prevents a score of 1.

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 is a noun fragment ('Cancellation tiers') that largely restates the name and title, with no verb stating what the tool does. It does add one real semantic detail — that tiers are counted from the start of the event — which clarifies what the returned data represents. It never distinguishes this tool from siblings like get_price_estimate or get_availability.

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?

No guidance on when to call this tool, no prerequisites (an event slug is required, but that's schema), and no mention of alternatives despite five sibling tools. An agent gets no help deciding between fetching a policy and fetching availability or a price estimate.

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/non-destructive, so the bar is lower, and the description still adds real behavioral context: the number is non-binding, extras such as electricity are excluded, and children up to 14 are free. What it omits is whether rates vary by season or when the quote could go stale.

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 pricing rules are dense and useful, but the German trailing sentence largely restates the English ('Richtpreis ohne Extras'), and the opening clause is grammatically fragmentary rather than front-loading the key caveat (non-binding estimate).

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 5-parameter tool with no output schema, the description should say what the response contains (total amount, currency, per-night breakdown). It explains the pricing formula but not the return shape, and event_slug is left unexplained.

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 0%, so the description must compensate. It explains adults, nights, category (via included_adults per category) and children (free up to 14), but event_slug is never mentioned and category_key is only obliquely referenced. Partial compensation leaves two parameters semantically thin.

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 resource (guide price for pitch and persons) and enumerates the driving inputs (category, adults, nights), which distinguishes it from siblings like create_reservation or get_availability. The telegraphic opening sentence ('Guide price for pitch and persons') is a bit compressed but still names verb-ish intent and scope.

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?

Implies usage via the caveat that extras are excluded and the binding amount appears in the booking form, which signals this is an indicative-only estimate. However, it never explicitly says when to call this versus get_booking_link or create_reservation, and no prerequisites (e.g., event must exist) are given.

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 it read-only, idempotent, non-destructive, and closed-world, so the description only needs to add value beyond that — and it does by disclosing the return shape (dates plus booking-open status), which is the main thing an agent needs here. No pagination, ordering, or error behavior is mentioned, so it is not a 5.

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 front-loaded sentences that identify the venue, the enumerated resource, and the fields returned. The German sentence restates the English verbatim, which is somewhat redundant but arguably serves a bilingual audience and costs little.

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 carries the burden of explaining what comes back, and it does name the returned fields (dates, booking-open status). It stops short of describing ordering, count, or how to follow up with a reservation, which would fully close the loop for a zero-parameter listing tool.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. It correctly avoids inventing parameter behavior.

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 ('List all events') and pins the scope to a named venue (Schitterhof CAMPING WEISS, Red Bull Ring), so the agent knows exactly what is enumerated. It does not explicitly contrast with get_availability or the other siblings, which keeps 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 description implies a discovery/browse use case by saying it lists dates and whether booking is open, but it never states when to call this rather than get_availability or get_booking_link. Usage is inferable from the resource, not directed.

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