Pilot-Next

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

With no annotations, the description carries the behavioral burden. It discloses the authorization model (pilot can cancel only own bookings; admin can cancel any), which is the key safety-relevant behavior. It does not state whether cancellation is reversible or whether it affects settlement, but the core mutation is clear.

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 front-loaded with the core purpose and is compact, though the all-caps 'ULTRA-PROACTIVE' block is somewhat emphatic. Every sentence carries operational weight and no filler is present.

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 mutation tool with no output schema, the description covers purpose, permissions, and ID sourcing. It could also mention edge cases such as already-canceled bookings or failure responses, but nothing essential to invoking the tool 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 schema already documents bookingId at 100% coverage, so the baseline is 3. The description adds value by telling the agent exactly how to obtain the ID (from get_my_bookings or the previous create_booking success message), which goes beyond the schema's generic 'ID of the booking to cancel.'

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 the specific action 'Cancel a booking,' naming both the verb and the resource. It then adds a clear scope distinction between pilot and admin permissions, which separates it from read-only siblings like get_my_bookings and from creation/settlement tools.

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 explicitly states when the tool applies and provides a concrete decision path: use get_my_bookings to find the ID or reuse the internal ID from create_booking, and never ask the user for an ID the agent can derive. This is direct when/when-not 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?

With no annotations, the description carries the transparency burden and does a solid job: it discloses the hard dependency on a validity token, the side effect that no booking exists unless this tool is called, and the requirement to output the returned summary. Missing details like error handling or authorization are notable but not fatal.

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 text is compact and organized with clear labels (CRITICAL, ONE-SHOT, ACTION), with every sentence carrying actionable information. No filler or 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?

For a side-effectful creation tool with no annotations and no output schema, the description covers prerequisites, date calculation, and mandatory return handling. It could be more complete by mentioning expected failure conditions or availability checks, but the essential invocation path is well specified.

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 baseline is 3; the description goes further by specifying how start/end years must be verified and where validityToken comes from. It adds critical operational meaning without needing to restate every property.

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 the operation ('Create a booking') and reinforces its one-shot nature. It does not, however, contrast itself with related siblings (e.g., find_available_slots or cancel_booking), so it falls just short of full 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 gives explicit operating context: verify the current year, use get_dispatch_context_and_time to confirm today's date, and calculate ISO dates from context rather than asking the user. It does not spell out when not to use the tool, but the prerequisites and workflow are clear.

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?

The description says 'call this IMMEDIATELY' and instructs to estimate duration, but does not disclose any behavioral aspects like whether the tool performs network calls, requires authentication, or has side effects. Since no annotations are provided, the description carries the full burden, and it fails to disclose basic operational behavior beyond the trigger conditions.

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 verbose and front-loads imperative commands in all caps, which is redundant. It repeats the instruction to estimate durationHours and uses excessive emphasis. The key information about the two types of hours is buried near the end. It could be condensed into two clear sentences.

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 tool's simplicity (3 optional parameters, no output schema), the description covers the main use case and the distinction between the two duration parameters. However, it lacks any mention of what the response format is (e.g., estimated cost in what currency) and does not specify whether aircraftId is necessary for a cost estimate, leaving some gaps for an agent.

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 schema already documents the parameters (aircraftId, durationHours, blockDurationHrs). The description adds guidance on how to estimate durationHours and explains the difference between durationHours and blockDurationHrs, which is useful. However, it does not clarify how aircraftId affects the cost or provide examples, so it adds some value but not extensive.

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 tool's purpose: estimating flight cost when the user asks about cost. However, it does not explicitly mention the resource (flight cost) in a concise way and leans heavily on imperative instructions rather than a clear declarative statement. It is distinguishable from siblings by its focus on cost estimation, but the wording is muddled.

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 explicit usage triggers ('If the user asks

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 no annotations, the description carries the full burden. It discloses an important precondition (must call get_dispatch_context_and_time first) and warns against guessing dates, which is valuable. However, it does not describe the return shape, failure behavior, or confirm the operation is read-only.

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 short and front-loaded with the core purpose, followed by a required prerequisite and a usage note. The all-caps warnings are attention-grabbing but not wasteful; every sentence serves a purpose.

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 and no annotations, the description gives the key prerequisite and a clear usage scenario but omits what the returned slots look like or how results should be interpreted. It is adequate for invocation but incomplete on output expectations.

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 reinforces that dates must come from context and that validityToken originates from get_dispatch_context_and_time, but those facts are already in the schema. It adds no new detail for aircraftId or durationHours.

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 'Find free flight slots,' a clear verb+resource statement that tells an agent the tool locates open time windows. It does not explicitly differentiate from siblings like get_aircraft_availability, so it stops short of a 5, but the core purpose 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?

The description gives explicit usage context: call get_dispatch_context_and_time first, and use this tool when a user asks to fly in order to find and suggest a gap. It does not state when not to use it or name alternative tools, so it lacks full exclusion 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?

With no annotations, the description carries the burden. It discloses the dependency, warns about year, and explains fleet-wide behavior when aircraftId is missing. However, it does not describe return format, error behavior, or other operational details that could affect 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?

The description is concise and well-structured, with the core purpose upfront followed by critical requirements and warnings. Every line earns its place, and the warnings are clearly highlighted.

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 covers the prerequisites and key usage, but does not explain what the tool returns or how it relates to similar tools like find_available_slots. For a simple check tool it is mostly complete, but lacks some context for agents to fully anticipate behavior.

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 baseline is 3. The description adds meaning beyond the schema by instructing to calculate from/to from context and not ask the user, and explaining the aircraftId omission behavior. This adds significant value.

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 'Check availability' which is a clear verb+resource but does not explicitly mention 'aircraft' or distinguish this from sibling tools like find_available_slots. The name carries the specificity, but the description itself is too vague and borders on tautology.

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?

Provides explicit system requirement to call get_dispatch_context_and_time first, a warning about year guessing, and conditional usage for aircraftId. This gives clear when-to-use context, though it does not mention when not to use it or compare to 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?

No annotations are given, so the description must carry the safety and side-effect profile. It explains the meaning of HOBBS and TACHO and the default parameter behavior, which is useful, but it never states this is a read-only operation, nor what it returns (both hours or one, units, etc.). With zero annotations, it leaves some operational ambiguity.

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 with no fluff. The core action is front-loaded, and the terminology clarification earns its place. Some might argue the terminology is essential, not filler. It is efficient and well-structured.

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 single-parameter read tool with no output schema, the description is mostly adequate but has gaps. It does not specify whether the response includes both HOBBS and TACHO or how they are returned (single value, list). Given the simplicity, it should have clarified the return shape to be 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?

The schema already covers aircraftId 100% with a good description, so the baseline is 3. The tool description adds meaningful semantics: it clarifies default behavior when omitted ('uses your default'). This goes beyond the schema and lifts the score to 4.

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 clear verb ('Get') and resource ('current hours'), and clarifies terminology (HOBBS vs TACHO). It is specific enough to distinguish from siblings like get_flight_statistics or get_aircraft_availability, though it could be more explicit (e.g., 'Get current Hobbs or Tacho hours').

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?

Offers almost no guidance on when to choose this tool over its siblings. It mentions that omitting aircraftId uses the default, which is a behavioral hint, but does not reference alternate tools like get_flight_statistics or situate itself in the workflow.

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 no annotations, the description carries the behavioral burden. It discloses that this is the start step, that the agent must present readings to the pilot, and that it must wait for confirmation before proceeding. It does not explicitly state whether the operation is read-only or describe response format, but the 'get' verb and workflow details provide reasonable transparency.

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 compact and well-structured with clear labeled sections (MANDATORY START STEP, INSTRUCTION, ACTION, CRITICAL). It front-loads the core purpose and uses imperative lines efficiently. The heavy use of capitalization is slightly noisy but not wasteful.

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 a single well-documented parameter, no output schema, and low complexity, the description covers the essential workflow: what to retrieve, what to tell the pilot, and what to wait for. It does not explain what 'available manual rates' are or how to use them, but an agent has enough 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?

The input schema fully documents bookingId as 'The UUID of the booking' with 100% coverage. The description adds no additional parameter-level detail, so the baseline of 3 is appropriate since the schema already carries the semantic weight.

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 the tool retrieves the system's recorded START values (Hobbs/Tacho) and available manual rates, which is a specific verb and resource. It does not explicitly contrast itself with sibling tools like preview_settlement or settle_booking, so it loses the top score for lacking direct 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 gives explicit when-to-use guidance: 'MANDATORY START STEP' and 'You MUST call this as soon as a flight to settle is identified.' It also provides a critical sequencing rule ('DO NOT ask for end data in the same message. WAIT for confirmation'). It stops short of naming alternative tools or exclusion conditions, so it is clear context without full when-not-to-use coverage.

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 no annotations provided, the description carries the full behavioral burden. It discloses that the call is a silent, non-interactive retrieval and that permission is already granted, avoiding unnecessary user prompts. It could add more about output shape or failure behavior, but for a zero-parameter read tool it is reasonably transparent.

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 compact and front-loaded, opening with exactly what the tool returns and then giving terse, actionable usage rules. Every sentence earns its place without redundancy.

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 no-parameter context-retrieval tool, the description is complete: it lists the returned context elements, explains that it is the first call each turn, and clarifies why it matters for temporal grounding. No additional information is needed for correct invocation.

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 the description cannot add parameter-level meaning. The schema coverage is 100% and there is nothing to document; the baseline 4 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 uses a specific verb ('Retrieves') and names a clear resource bundle: active fleet, default aircraft, user preferences, and current date/time. This distinguishes it from all sibling tools, which are domain operations rather than a context-gathering utility.

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 explicit, unambiguous usage instructions: call silently at the start of every turn, do not ask the user, and always call first to ground temporal queries. This leaves no doubt about when and how the agent should invoke it.

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 no annotations, the description carries the full burden of behavioral disclosure. It discloses a critical external dependency on get_dispatch_context_and_time, which is useful, but it does not describe the return format, whether the operation is read-only, or what specific statistics are included.

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 sentences with no filler. The core purpose is front-loaded, and the IMPORTANT prerequisite is clearly highlighted without unnecessary detail.

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?

Because there is no output schema, the description should explain what the tool returns, but it only says 'flight hour statistics' without defining the granularity, fields, or aggregation. The prerequisite is helpful, but the missing return-shape information leaves an agent uncertain about the tool's actual result.

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 schema already documents both parameters, but the description adds meaningful context about the 'year' parameter: the current year is not assumed from the system clock and must be obtained via the context tool. This goes beyond the schema's 'default current year' note.

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 clear verb and resource: 'Get flight hour statistics.' However, it does not distinguish this tool from sibling 'get_aircraft_hours,' leaving some ambiguity about whether these are the same or different capabilities.

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 one explicit and important usage prerequisite: call get_dispatch_context_and_time first to know the current year. It does not, however, explain when to prefer this tool over alternatives like get_aircraft_hours or specify any exclusion 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?

There are no annotations, so the description carries the full disclosure burden. It does mention the default scope ('checks all' when aircraftId is omitted) and the dependency on current date/time, but it does not describe the output shape, edge cases, or whether the action is purely read-only. Still, the most important behavioral trap is front-loaded.

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 concise sentences with no wasted words. The first states the tool's purpose, and the second conveys the essential call-order prerequisite for accurate results.

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 one-optional-parameter tool with no output schema, the description covers the necessary prerequisite and the parameter behavior. It leaves minor room for ambiguity about the exact shape of returned maintenance data, but overall it is sufficient for correct usage.

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 schema already fully documents aircraftId, so the baseline is elevated. The description adds valuable context beyond the schema by stating that omitting the parameter checks all aircraft, which is not encoded in the input 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 verb and resource ('Forecast maintenance dates') and clarifies the optional aircraft scope. This makes it easy to distinguish from sibling tools like get_aircraft_hours or get_aircraft_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?

The description gives clear operational guidance: it tells the agent to call get_dispatch_context_and_time first for accurate 'days remaining', and explains the behavior when aircraftId is omitted. It does not explicitly contrast with alternative tools, but the instruction is enough to use this tool effectively.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'Get', implying a read operation, but does not disclose whether authentication is required, whether the balance is real-time or cached, or what the returned value represents beyond 'account balance'.

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 a single concise sentence with no filler. It is front-loaded and clear, though it is minimal enough that it does not fully compensate for missing usage or behavioral guidance.

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 getter with one optional parameter and no nested objects, the description is functional. However, there is no output schema and the description does not clarify return format, currency, or how this relates to settlement-related sibling tools, leaving some context 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 description coverage is 100%: the only parameter, check_reason, is already documented as 'Optional reason for checking the balance.' The tool description adds no additional parameter context, so the baseline score of 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 states a specific verb ('Get') and a clear resource ('current account balance'). It is unambiguous about what the tool does, though it does not explicitly differentiate itself from related settlement/balance siblings like get_booking_settlement_info or preview_settlement.

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 no guidance on when to use this tool versus alternatives such as get_my_bookings or get_booking_settlement_info. It gives no context, prerequisites, or exclusions.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'upcoming and recent bookings' without explaining what 'recent' means, whether the result is sorted, whether it includes cancelled bookings, or what the response shape looks like. This is a significant gap for a read tool with no annotation support.

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 a single short sentence that is front-loaded with the verb and resource. It is concise and easy to parse, though it could add a bit more context without becoming bloated.

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 annotations, no output schema, and only one optional parameter, the description is too thin. It doesn't clarify the meaning of 'recent', the default limit behavior, or the return format. An agent would need to infer too much to use it 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 schema already documents the 'limit' parameter. The description adds no additional meaning beyond what the schema provides, so the 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 states a clear verb ('Get') and resource ('your upcoming and recent bookings'), which distinguishes it from siblings like get_unsettled_bookings or get_booking_settlement_info. It doesn't explicitly name a sibling alternative, but the scope is specific enough for an agent to understand the tool's purpose.

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 usage for retrieving the user's own bookings, but it doesn't explicitly state when to use this tool versus alternatives like get_unsettled_bookings or get_flight_statistics. There is no exclusion or alternative guidance, so the agent must infer the context from the wording.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It only says 'Get', which implies a read-only operation, but it does not mention return format, pagination, potential need for permissions, or what happens if the pilot is not found. This is minimal and lacks transparency beyond the verb itself.

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 a single concise sentence with no filler words. It is front-loaded with the key action and resource. While it is short, it is not bloated, and the brevity is not penalized given the simple one-parameter tool. A slightly longer description could improve other dimensions without hurting 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?

There is no output schema, so the description should explain what 'flight activity' contains or what the response looks like. It does not. It also fails to provide any context about time ranges, data granularity, or how it relates to similar tools. This is incomplete for an agent to invoke correctly and interpret results.

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 schema covers 100% of the parameter descriptions, with 'name' described as 'Name of the pilot'. The tool description adds no extra meaning beyond this, but the schema already provides sufficient clarity for the single parameter. 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 uses a clear verb ('Get') and resource ('flight activity for a pilot'). It specifies the entity (pilot) and the general data type. However, 'flight activity' is somewhat ambiguous and does not distinguish it from siblings like get_flight_statistics, but it is not a tautology and conveys a direct operation.

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 no guidance on when to use this tool versus alternatives. It does not mention any context, exclusions, or mention related tools such as get_flight_statistics or get_aircraft_hours. A user or agent has no basis for choosing this over siblings.

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 zero annotations, the description must carry behavioral context. The verb 'Find' and the tool name 'get_' clearly indicate a read-only operation, which is sufficient. The description also specifies the return set (flights that are flown but unsettled). It does not mention pagination or whether it modifies data, but the non-destructive nature is unambiguous from the naming and verb.

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 a single, front-loaded sentence with zero fluff. Every word adds value: 'your flights' (scope), 'flown but not yet settled' (filter). It is concise while carrying the essential 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 simple list query with one optional parameter and no output schema, the description is adequate. It tells the filtering condition and implies the return is the user's own unsettled flights. It does not describe the returned booking object's fields, but since sibling tools like create_booking and get_booking_settlement_info share the same booking concept, this is not a major gap. A minor mention of pagination could be added, but the schema partially covers it.

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% for the only parameter (limit), which fully documents it ('Number of results (default: 5).'). The description does not add anything about the parameter, but per rubric, when schema coverage is high, a baseline of 3 is appropriate. The description's omission of limit detail is acceptable because the schema already provides complete information.

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 the tool's purpose with a specific condition ('flights that have been flown but not yet settled'). The verb 'Find' and the singular focus on unsettled bookings distinguish it from sibling tools like get_my_bookings (all bookings) and get_booking_settlement_info (details of a specific booking). An agent can immediately understand what this tool returns without opening the 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?

The description tells what the tool does but does not explicitly explain when to use it compared to other booking tools. Sibling tools like settle_booking and get_booking_settlement_info suggest a settlement workflow, and the description implies it is for identifying pending settlements, but it does not name alternatives or give routing guidance. However, for a simple list query, this level of guidance is acceptable.

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?

There are no annotations, so the description carries the behavioral disclosure burden. It usefully discloses that data is real-time, includes both METAR and TAF, and supports multiple stations. However, it does not mention response shape, error behavior, or what happens for invalid ICAO codes, which are relevant for a tool with no 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?

A single, front-loaded sentence with no wasted words. It communicates the core action, data type, and input scope efficiently.

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 one-parameter tool with no output schema, the description provides enough to understand input and expected result type. It omits fine-grained output format details, but the tool is low in complexity and the description covers the essential contract.

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%: the stations parameter is fully described as a list of ICAO codes with an example. The description's mention of 'one or more' aligns with the schema but adds no new parameter meaning. 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 states a specific verb ('Fetches'), a well-defined resource (METAR observation and TAF forecast), and the target input (ICAO stations). It is clearly distinguishable from all sibling tools, none of which involve weather.

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 makes the tool's context clear: retrieve real-time weather observations and forecasts for ICAO stations. There are no alternative weather tools among the siblings, so no exclusion is needed. It lacks explicit when-to-use phrasing but the intended use is obvious from the resource named.

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 no annotations, the description carries the full burden. 'Preview' and 'pre-confirmation' strongly imply a non-mutating operationcher. However, it never explicitly states that no record is created or changed, nor does it describe response contents beyond 'show the breakdown.' Some behavioral ambiguity remains.

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 short labeled sections plus an example. Information density is high; each line adds either a constraint, a usage direction, or a data-shape clarification. The all-caps labels are stylistically heavy but aid scanning.

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 covers purpose, timing, prerequisite data, and the object example. Missing, given no annotations or output schema, are explicit non-mutation guarantees-checklist, pricing details, or what the function returns. It is adequate but not fully self-sufficient for an agent deciding whether this operation is safe to call mid-booking.

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 covers all parameter names/types, so baseline is 3. The description adds a concrete example for the charges array and a warning that quantity must be a number, which highlights a likely failure mode. The prerequisite ('gathered all end data') also gives context for finalHobbs/finalTacho without duplicating schema text.

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–object pair, 'Preview the costs,' and frames it as a 'PRE-CONFIRMATION STEP' that 'show[s] the pilot the breakdown before generating the invoice.' This makes the tool's role clear, though it doesn't distinguish it from the similarly named sibling settle_booking or estimate_flight_cost.

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 concrete usage context: a mandatory prerequisite ('gathered all end data and manual charges ONE BY ONE') and the intended moment to call it ('before generating the invoice'). It lacks explicit 'use instead of X' routing, but the timing and preconditions are specific enough to guide selection.

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 no annotations provided, the description must carry behavioral context. It clearly states this is a finalizing action (generates invoice) and implies irreversibility by calling it the final step. It also warns against premature invocation. However, it doesn't mention what happens if it's called with isServiceFlight=true (no invoice), which is a schema detail but still behavioral. Overall, it provides solid context for a mutating action.

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 extremely concise—just two sentences. It front-loads the critical flag ('FINAL STEP') and the prerequisite, making it unmissable. Every word serves a purpose, and the capitalized labels draw immediate attention without cluttering.

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 finalizing tool with explicit prerequisites and a schema that fully documents parameters, this description is complete. An agent knows exactly when to call it and what it accomplishes. There's no output schema, and none is needed to justify the invocation. The emphasis on prerequisites is essential context.

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 all 8 parameters are already documented in the schema. The description adds nothing specific about parameter meanings beyond that, which is acceptable given the schema's completeness. The baseline of 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 states 'Finalize the settlement and generate the invoice' with a specific verb and clear outcome. It distinguishes itself as the final step after preview_settlement, and the naming convention plus the 'FINAL STEP' label make its role 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 explicitly lays out the prerequisite: must have called 'preview_settlement' and received explicit confirmation from the pilot. The 'CRITICAL' warning reinforces when NOT to call it. This is actionable and leaves no ambiguity about the required preceding action.

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