CGC Airport Transfers

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral context beyond them, including closure semantics (available:false with the closure message), partial closures affecting only some vehicles, blackout windows, and after-hours fee exposure that surfaces in the quote before booking.

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 core answer (whether a pre-booked pickup is possible) is front-loaded, and every following sentence carries a distinct rule. It is dense and packs several clauses into single sentences, but there is no filler.

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 usefully explains the available:false return path and closure messaging. Remaining gaps are minor: it does not describe the positive return shape or note that pax caps at 14, though the schema covers the latter.

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 date/time/pax formats are already documented; the baseline would be 3. The description earns above baseline by giving the date and time parameters real business meaning: standard rates 6am–9pm AEST, after-hours fee outside that window, and the 12-hour direct-contact rule.

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: whether CGC can take a pre-booked pickup at a given date and time. This is clearly distinct from get_quote, get_service_info, and request_booking, though it never names or contrasts those siblings 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 real when-not guidance: same-day requests should phone 0416 131 285, travel within 12 hours needs direct contact, and Christmas Day is closed. It does not, however, route the agent to any alternative sibling tool (e.g. use get_quote for pricing, request_booking to actually book), which keeps it short of a 5.

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?

With annotations declaring readOnlyHint=true and openWorldHint=false, the description adds rich behavioral context: pricing rules (AUD, GST, tolls, no surge), return handling (fares_aud one-way, return_totals_aud for full return, return discount logic), stops handling (detour pricing, no book_url with stops), closure handling (Christmas Day, blackout windows), and the importance of using the returned book_url with utm tags. This goes well beyond the annotations.

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 front-loaded with the core purpose and packed with relevant information. Every sentence contributes something useful, though the dense paragraph could be better structured with bullet points for readability. No redundant statements, but the length is near the upper limit for conciseness.

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 the complexity (17 parameters, nested objects) and the absence of an output schema, the description covers key return values (fares_aud, return_totals_aud, totals_aud, book_url, book_urls, available) and behavioral nuances. It does not fully describe the complete response structure (e.g., per-vehicle details), leaving some gaps, but it is sufficient for an agent to invoke the tool correctly and interpret the main outcomes.

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 parameter meanings are already well-documented. The description adds value by explaining interactions: how return_date adds return_totals_aud, how return_pickup/return_dropoff affect pricing on returns, and how stops generate totals_aud or return_totals_aud without a book_url. This exceeds the baseline of 3 by clarifying parameter effects beyond individual definitions.

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 opens with a specific verb and resource: 'Exact fixed prices for a transfer between two locations, straight from the live booking engine.' It clearly distinguishes the tool from request_booking by noting that quotes with stops must be booked via request_booking. An agent can tell this is the tool for getting fixed-price transfer quotes.

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 gives clear context for use: pass various trip details to get a book_url, and use request_booking for booking when stops are present. However, it does not explicitly state when to use this tool versus check_availability or get_service_info, leaving some ambiguity about alternatives.

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 and openWorldHint=false, so the safe, static, self-contained read profile is covered. The description adds useful domain disambiguation ('private pre-booked transfers, not a taxi or rideshare') but says nothing about return format or whether the data is static/cached.

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 tight sentences with no filler: the first enumerates the returned facts, the second disambiguates the service model. The core payload is front-loaded.

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 return burden and does so by enumerating the fact categories. It is complete for a parameterless lookup tool, though it could note that all facts are returned in one 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?

The tool takes zero parameters, so the schema imposes no semantic burden and the baseline is 4. Nothing in the description is needed to explain inputs.

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 (retrieves business facts) and enumerates the exact resource contents: contact, hours, fleet, inclusions, policies. This clearly separates it from the transactional siblings (check_availability, get_quote, request_booking) without needing to name them.

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 implied by content type — an agent can infer this answers 'about the business' questions rather than pricing or booking — but there is no explicit when/when-not statement or pointer to the sibling tools that handle the transactional cases.

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 this is a non-readonly, open-world, non-idempotent write with destructiveHint=false. The description adds meaningful behavior beyond that: no payment is taken through the tool, a secure checkout_url is returned, refusals happen before lodging, and agent_key is required.

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 most important facts are front-loaded: what it does, the checkout_url return, and that payment is not taken through the tool. The paragraph is dense but appropriately sized for a complex 28-parameter booking tool, with little obvious 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?

With no output schema, the description explains the key return value (checkout_url) and important refusal behavior. For a complex booking mutation, it is largely complete, though it could say more about duplicate submissions or other failure modes beyond closed days and blackout windows.

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 82%, so the schema already carries most parameter meaning. The description adds useful context for stops/return_stops matching the quoted get_quote and for obtaining agent_key, but does not clarify many of the 28 parameters beyond what the schema 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?

The description states a specific verb and resource: 'Lodge a booking', and explains that success returns a checkout_url. It references get_quote for the quoted stops, but does not explicitly distinguish this tool from check_availability or get_service_info, so sibling differentiation is only partial.

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 context for use: after a get_quote, with an agent_key, and notes that closed-day or blackout-window pickups are refused. It does not explicitly state when to use check_availability or get_service_info instead, but the booking-specific guidance is strong.

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