Airport Transfer Connect

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description adds the useful detail that results include which vehicles fit, but says nothing about whether an availability result is a hold, how live the data is, or any rate/latency characteristics.

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?

A single front-loaded sentence with no filler; the scope and the result content are stated immediately. Slightly compound, but nothing is redundant enough to trim.

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 9-parameter, open-world, non-destructive check with no output schema, the description is adequate but thin: it hints at a vehicle-fitness result without describing the shape of the response or what an unavailable outcome looks like. It also doesn't mention round trips (return_date/return_time) or luggage constraints even though the schema supports them.

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%, including formats, defaults, aliases, and airport-pickup time guidance, so the schema does the heavy lifting. The description only echoes route, date/time, and passengers and adds no meaning beyond that; it ignores luggage, flight_number, and the return-trip parameters entirely.

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 ('check whether a private transfer can be booked') plus the key inputs (route, date/time, passenger count) and the return content ('which vehicles fit'). It clearly differs from get_quote and request_booking in substance, but never names 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?

Use is implied as a pre-booking feasibility check, but there is no explicit when-to-use vs when-not guidance, and no routing to get_quote (for pricing) or request_booking (to actually book). An agent must infer the sequence from the names alone.

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, non-destructive, open-world), and the description adds real context on top: the currency and tax basis (EUR, VAT incl., per vehicle), the vehicle classes returned (E-Class, V-Class, S-Class) and the presence of a prefilled booking_url. That is useful behavioral information about the response shape for a tool with no output schema. It does not mention error or no-route behaviour, which would be the next useful disclosure.

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 sentences, front-loaded with the core purpose, and no filler. The brand name and example are justified because they disambiguate the domain. A slightly tighter phrasing could still fold the returned fields into one clause rather than a list.

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 nine-parameter read-only quote tool with a fully documented schema and no output schema, the description supplies exactly what is missing: what the call returns, in what currency and on what basis, plus the vehicle tiers. Nothing an agent needs to invoke it correctly is absent, though an explicit pointer to request_booking would be a nice addition.

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%, with each parameter documenting itself including airport codes, date/time formats and accepted aliases, so the schema does the heavy lifting. The description adds only the 'per vehicle' pricing basis, which is pricing semantics rather than parameter semantics. Baseline 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 opens with a specific verb-and-resource pair ('Live fixed price ... for a private transfer/chauffeur ride') and anchors it with a concrete example (CDG airport to a Paris hotel), which makes the tool's scope immediately clear. It stops short of naming its siblings check_availability and request_booking, so an agent must infer the division of labour between quoting, availability and booking rather than being told.

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: the mention of a 'prefilled booking_url' signals this is a pre-booking pricing step, and 'availability' in the return set hints at overlap with check_availability. There is no explicit when-to-use / when-not-to-use statement and no routing to either sibling, which is a gap given there are two closely related tools in the same namespace.

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 declare a non-read-only, non-destructive, open-world write operation; the description adds meaningful context beyond that by disclosing the consent requirement and that payment/confirmation happens outside this call at the returned booking_url. That distinction (request vs. confirmed booking, no charge taken here) is exactly the behavioral nuance an agent needs. It does not mention failure modes or what happens if the request is later rejected.

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 sentences, no filler: the action and consent constraint come first, and the return behavior follows. Every clause carries information the agent cannot get from the structured fields.

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 14-parameter mutation with no output schema, the description usefully documents the return values (a reference and a prefilled booking_url) and the consent requirement. It stops short of explaining sequencing with the sibling tools or pricing expectations, which is the main 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 description coverage is 93%, so the schema already carries nearly all parameter meaning. The description only restates that name, email, and phone are required, which duplicates the schema's required list, and adds no clarification for the 14 parameters or their ranges.

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 uses a specific verb+resource ("Register a booking request for the passenger") and makes clear this produces a request, not a confirmed reservation, which distinguishes it from check_availability and get_quote by implication. It does not name the siblings explicitly, so an agent must infer the boundary rather than read it.

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 states a real precondition ("only with the user's explicit consent") and clarifies the downstream flow (passenger confirms and pays via booking_url), which tells the agent this is not the final booking step. However, it gives no guidance on whether check_availability or get_quote should be called first, and no exclusion cases.

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