CGC Airport Transfers

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuine behavioral context beyond that: service windows (6am-9pm), the surcharge consequence of out-of-hours pre-booking, and the constraint that travel within 12 hours cannot be handled here. It does not describe the shape of the answer, which is a minor gap.

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?

Three tight sentences with no filler, front-loading the core purpose before the hours and fee caveats. The density of rules in the second and third sentences is high but each clause carries operational meaning.

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 read-only availability check with no output schema, the description covers purpose, service hours, pricing side-effects, and an escalation rule. The main omission is what a positive or negative result looks like, but with a simple boolean-style check that is a small 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 100%, so date, time, and pax are already fully documented with formats and the 1-14 passenger range. The description adds no parameter-level detail, which is acceptable given the schema does the work, but it earns only the baseline.

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 check (can CGC service a pickup) on clear resources (date and time), so the agent knows this is a feasibility lookup rather than a booking or pricing call. It is distinguishable from request_booking and get_quote, though it never names those siblings directly.

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 supplies useful operating conditions — standard hours, out-of-hours fees, and a 12-hour lead-time rule requiring direct contact — which imply when this tool is appropriate. However, it never explicitly routes the agent to alternatives (e.g. get_quote for the fee amount), so selection guidance is only implied.

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 only readOnlyHint=true provided, the description carries rich behavioral context: prices are locked at booking with no surge, the no-fixed-price response is disclosed, and the return payload (book_url per vehicle in book_urls) is described despite the absence of an 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?

Four dense sentences, front-loaded with the core purpose and ending with the actionable instruction. Some clauses (GST and tolls, no surge) are compact value-adds rather than filler, though it runs slightly long.

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 13-parameter pricing tool with a nested seats object and no output schema, the description covers pricing semantics, the no-price edge case, and the return structure (book_url/book_urls). Nothing an agent needs to call it or relay results is missing.

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 baseline is 3; the description adds rationale by explaining that date, time, passengers, return leg, luggage, child seats and flight should all be passed because they are embedded into the generated book_url, which the schema only partially conveys.

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 and scope: exact fixed transfer prices from the live booking engine, per vehicle, AUD, GST/tolls included. An agent can distinguish this pricing lookup from check_availability, get_service_info, and request_booking without inspecting 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?

Gives clear operational guidance: pass all trip details so the link carries them, hand the customer book_url rather than describing the form, and never estimate a figure if no fixed price exists. It does not explicitly name the sibling tools (e.g. request_booking) or state when to prefer them, so it falls 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?

readOnlyHint=true is consistent with a static-facts lookup, so no contradiction. The description adds the content scope (which fact categories are covered) but nothing beyond that — no note that the data is static/cacheable or what the response looks like. Adequate given annotations carry the safety signal.

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 short sentences, front-loaded with the resource and its contents, with the disambiguating note last. No filler or repetition of the name.

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 zero-parameter, read-only info lookup with no output schema, the description covers what facts are returned and what the business is. The only gap is that it never frames the result as a fixed business profile versus live data, but nothing an agent needs to invoke it correctly is missing.

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, which is the baseline-4 case per the rubric. Nothing in the description needs to explain inputs, and it correctly implies the call is context-free.

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 (CGC Airport Transfers business facts) and enumerates the categories returned: contact, hours, fleet, inclusions, policies. The clarifying line distinguishes the business model from taxi/rideshare, but it differentiates the service rather than this tool from its action siblings (get_quote, request_booking), so it stops 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?

Usage is only implied: an agent can infer this is the static-information lookup versus the transactional siblings, but no sentence says when to call it or when to prefer check_availability or get_quote instead. The 'not a taxi or rideshare' line is scope clarification about the business, not tool-selection 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 carry only readOnlyHint=false, so the description bears most of the burden and delivers real substance: no payment is taken through the tool, the return is a secure checkout_url, an agent_key must be obtained from an admin, and terms_accepted must not be set without an explicit customer yes. It omits what happens on failure, whether bookings can be amended/cancelled, or any rate limits.

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?

Three tight sentences with zero waste, front-loaded with what the tool does before moving to the return value and the credential requirement. Every sentence earns 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 22-parameter write tool with no output schema, the description supplies the critical agent-facing context (auth requirement, checkout_url return, payment never handled here, terms gate). It stops short of covering error behavior and the pricing/optional-parameter interactions, but the schema handles most field-level detail.

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 77%, but the description adds meaning the schema lacks: it explains the agent_key provenance (contact admin@cgctransfers.com.au) and enforces the correct semantics of terms_accepted. It does not touch other nuanced fields such as seat_qty vs child_seats or the return_date/return_time pairing.

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+resource ("Lodge a booking"), and the mechanism is concrete: it returns a checkout_url for payment. It does not explicitly distinguish itself from siblings (check_availability, get_quote, get_service_info), which is the only thing keeping it from 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?

Usage is implied through the workflow (get a quote/availability, then lodge), and it tells the agent to hand the checkout_url to the customer rather than pay. However, it never states when to prefer this over get_quote or check_availability, nor any prerequisites such as confirming availability first.

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