OrangeRide Gatwick transfers

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds that the tool returns factual reference information rather than performing actions, but it does not state freshness, source reliability, or whether the content is static.

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 names the resource and then lists the covered topics. There is no redundant or filler wording.

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 simple no-parameter reference tool with no output schema, listing the topics is enough for an agent to know what information is available. Completeness would improve with a note on freshness or a clearer distinction from transactional siblings, but no essential calling information 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 has zero parameters, so parameter semantics are not applicable and the baseline is 4. The description correctly implies a no-argument informational call.

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 resource (OrangeRide facts) and enumerates the covered topics: area, booking notice, payment, Gatwick meeting points, flight tracking, and contact details. It is clear enough to distinguish a general reference tool from transactional siblings like request_booking or confirm_booking, though the verb 'facts about' is somewhat broad.

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 enumerated topics imply when to use the tool—when an agent needs general service information—but there is no explicit when-to-use or when-not-to-use guidance. Alternatives such as check_flight for flight status or get_quote for pricing are not mentioned, leaving the agent to infer 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 establish that this is a safe, read-only, idempotent lookup. The description adds that both the booking reference and the booking mobile are required, which is useful operational context, but it does not explain mismatch handling, error behavior, or what status information is returned.

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 two short sentences and front-loads the core purpose before the required inputs. There is no unnecessary wording.

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 simple two-parameter read-only lookup, the description supplies the purpose and required identifiers needed to invoke it correctly. It is slightly incomplete because it does not describe returned status values or lookup failure behavior, but the annotations carry the safety profile.

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 schema already documents both required parameters. The description restates that the reference and mobile are needed, but adds no format, syntax, or matching semantics beyond the schema fields.

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 clearly states a specific verb and resource: retrieving the status of one OrangeRide booking. It is distinguishable from request_booking and confirm_booking by implication, but it does not explicitly name or contrast those siblings.

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 provides the important prerequisite that the caller needs the reference and the mobile number used for booking. However, it gives no explicit when-to-use guidance versus siblings such as confirm_booking or request_booking, and no exclusions or failure conditions.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: results are scoped to Gatwick arrivals and the landing time is expressed in UK time, which matters for pickup planning. No mention of failure behavior for unknown flight numbers or how far ahead dates are valid.

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, zero filler. The core capability and returned fields come first, and the use-case hint is compressed into a trailing clause rather than a paragraph.

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 lists the four returned fields, so an agent knows what it will get back. It would be fully complete with a note on behavior for invalid or not-yet-scheduled flights, but for a simple two-parameter lookup it is largely sufficient.

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 both flight_number and date already documented including format and an example, so the schema carries the load. The description's only added nuance is that the landing time is UK time, which reinforces rather than extends the schema's 'UK date the flight lands'. 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?

States a specific verb (check) and a bounded resource (a flight landing at Gatwick), then enumerates exactly what comes back: airline, origin, scheduled landing in UK time, and terminal. The Gatwick constraint makes the scope unambiguous even against the booking-oriented siblings.

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 for pickups from Gatwick' gives a concrete scenario that tells the agent when this tool is appropriate, tying it to the airport-transfer workflow. It does not name a when-not case or point to an alternative, so it stops short of full routing 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 non-readOnly, openWorld, non-idempotent, non-destructive, so the safety profile is covered. The description adds real behavioral context the annotations cannot convey: this is not the final confirmation — OrangeRide sends the user a text to confirm, and a reference is returned. It stops short of saying what happens on an invalid code or whether repeated calls send additional texts.

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 short sentences, front-loaded with the action, then the return value, then the critical caveat. No filler, and the capitalized REQUEST emphasis is the one place emphasis is warranted.

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 two-parameter tool with no output schema, the description covers the action, the return value, and the two-step confirmation flow. Missing only failure modes (invalid or expired code) and the consequence of duplicate calls, which a caller would likely need.

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 both parameters are documented (code as the 6-digit texted code, verification_id as coming from request_booking). The description restates the code's origin without adding format, length, or validation semantics beyond the schema, so the 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?

States a specific action (send the booking request with the texted code) and a concrete return value (a reference). It also clarifies the non-obvious semantics that this is a request stage rather than a final confirmation, which separates it from a plain 'confirm' reading. It does not explicitly contrast with siblings like request_booking or booking_status, so it falls 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 implied: the user must already have received a code by text, and the verification_id must come from request_booking (stated in the schema). There is no explicit statement of when not to call it, what to do if the code is wrong or expired, or which sibling to use for status checks afterward.

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 real value beyond that: it discloses the result cardinality ('up to 5 matches'), what the matches contain (ids), and a hard-coded exception that would otherwise cause a silent wrong call. It stops short of noting what happens on zero matches or whether the query is normalized, which keeps it from 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?

Three short sentences, each doing distinct work: purpose, return contract plus downstream use, then the exclusion. The most failure-prone information (the Gatwick carve-out) is placed last where it is still prominent, and no sentence restates the title or annotations.

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 lookup with no output schema, the description covers what goes in, what comes back in shape and quantity, how the output is consumed downstream, and the single known edge case. Annotations handle the safety semantics, so nothing an agent needs to call this 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?

Schema coverage is 100% and the single parameter already carries an example, so the baseline is 3. The description still adds meaning by naming the accepted categories of input (street address, postcode, station, hotel), which is broader than the schema's two examples and tells the agent free-text user utterances are acceptable.

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 ('Look up a UK pickup or drop-off place') and enumerates the entity types it resolves (street address, postcode, station, hotel). It also names the downstream consumer (get_quote) and the one case it must not be used for, so an agent can separate it from siblings without opening a 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 an explicit use case (resolving a place to ids that feed get_quote) and an explicit exclusion with the alternative to use instead ('Not for Gatwick Airport: use the ids gatwick_north or gatwick_south'). When-to-use, when-not-to-use, and the substitute are all present.

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. The description adds genuinely new behavior: the quote_id expires after 30 minutes and ties into the booking flow, and results differ in nature depending on whether date/time are present.

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 compact sentences with zero filler, and the primary behavior (fixed fare) is front-loaded before the input-dependent distinction. Nothing is repeated from the title or schema.

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-value burden and does name the two key outputs (fare and quote_id). For a 6-parameter read tool this is nearly sufficient; only edge behavior around optional passenger/suitcase counts is left implicit.

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 67%, so the schema already documents pickup_id, destination_id, date and time formats. The description adds meaning about how date, time, passengers and suitcases jointly produce an exact fare, but says nothing about what happens when passengers/suitcases are omitted or how they change the price beyond their inclusion in the exact-fare case.

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?

"Fixed fare for a trip" names the resource and the returned artifact (fare), and the two sentences make the exact-quote vs 'from'-price distinction explicit. It does not name a sibling tool to contrast with (e.g. suggest_pickup_time or check_flight), so it falls short of full sibling differentiation.

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 clearly conditions usage on inputs: supply date+time for an exact fare and a bookable quote_id, omit them for a typical daytime starting price. That is actionable context, though it never states exclusions or which sibling to use instead (e.g. when to use suggest_pickup_time to obtain the time).

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 establish that this is a non-read-only, open-world, non-idempotent, non-destructive operation. The description adds important behavior not captured there: it sends a 6-digit SMS code to the user's mobile and must be followed by confirm_booking. It does not describe failure modes, rate limiting, or duplicate-request behavior, but the key side effect and workflow dependency are 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 three short sentences, front-loads the main action and precondition, and then gives the operational sequence. Every sentence contributes to correct invocation or follow-up behavior.

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 mutating booking-initiation tool with no output schema, the description provides the essential flow: start the request, expect an SMS code, ask the user for it, and call confirm_booking. It also includes the user-facing prerequisite of reading back trip and fare, which is enough for an agent to invoke the tool correctly.

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 parameter names, constraints, and per-field descriptions already do most of the work. The description adds useful context that quote_id must correspond to a quote the user has agreed to and that mobile receives the code, but it does not meaningfully expand semantics 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?

The description states a specific action—starting a booking request for an already-agreed quote—and immediately names the follow-up tool confirm_booking. It clearly distinguishes the initiation step from confirmation and from quote retrieval.

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 specifies the precondition (the user has agreed to a quote), the workflow after calling (text code, ask user for it, call confirm_booking), and a sequencing constraint (only after reading trip and fare back to the user). This is explicit enough to guide both when and how to use the tool.

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 and closed-world, so the safety profile is covered. The description adds real value beyond that by disclosing the actual computation: arrival 2 hours before departure, plus drive time, plus 10 minutes spare, making the result predictable without invocation.

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?

One sentence with a front-loaded usage condition and a parenthetical that carries the entire algorithm. No filler, no restatement of the title or annotations.

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?

The description explains the core calculation but says nothing about what the tool returns (a lone time? a full itinerary?) or how terminal_id affects the drive component, and with no output schema the description carries that burden. For a 5-parameter tool it is adequate but leaves real 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 coverage is 100%, so every parameter is already documented, and the baseline of 3 applies. The description restates the 2-hours-before-flight rule but does not explain how the optional at_airport_by override interacts with that default, even though the schema flags it as a user-supplied alternative.

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 gives a specific verb and computed output ('works out the pickup time') and scopes it to a narrow scenario ('a trip to Gatwick to catch a flight'), which distinguishes it from quote/booking siblings. It stops short of naming an alternative tool, but the scope restriction does the differentiation work.

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?

'For a trip to Gatwick to catch a flight' is an implicit when-to-use condition, so the intent is inferable. There is no explicit statement of when not to use it, no mention of prerequisites such as needing a pickup_id from find_place first, and no routing to get_quote or request_booking.

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