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

With no annotations, the description carries the transparency burden. It explicitly discloses that the tool returns a temporary xlsx download link valid for 24 hours and containing 5 sheets, and the verb '查询' signals a read-only operation. It omits auth/rate-limit details, but for a read-only statistics tool the output artifact and TTL disclosure are meaningful.

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 dense sentence that front-loads the purpose, then lists metrics, query dimensions, and the output artifact. It is compact and free of filler, though the metric list is somewhat run-on.

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 report-generation tool with no output schema, the description covers the essential contract: input dimensions, output artifact, validity period, and sheet count. It could name the five sheets or clarify empty-data behavior, but an agent has enough to invoke it and handle the 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?

Schema description coverage is 100%, so the schema already documents airline, start/end dates, and passenger type. The description only restates these as query dimensions without adding new semantic details, matching the baseline for fully covered schemas.

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 identifies the resource ('指定航司') and the operation ('统计周期内运行全貌'), enumerates the metrics, and states that it returns an xlsx download link. It does not explicitly name sibling alternatives, so it falls short of top marks, but the airline scope distinguishes it from dast_airport_operation_statistics.

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?

No when-to-use guidance, exclusions, or alternative tool references are provided. The phrase '按航司、开始日期、结束日期、运输类型查询' describes parameter usage, not when to choose this tool over siblings like dast_flight_overview_daily or dast_airport_operation_statistics.

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 disclosure burden. It adds useful behavioral detail by stating the output format ('xlsx下载链接'), the validity period ('24小时有效'), and the number of sheets ('6个sheet'). For a read-only statistics tool, this is meaningful transparency beyond the bare query semantics.

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: it front-loads the result metrics, then the query dimensions, then the output artifact. Every sentence contributes necessary information with 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 tool with no output schema, the description adequately covers all four required parameters and communicates the return mechanism (a temporary xlsx link with six sheets). It stops short of enumerating the six sheet names or their exact columns, but for the purpose of invoking the tool this is sufficiently 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?

Schema description coverage is 100%, so the baseline is 3. The description only restates the parameter categories ('按机场、开始日期、结束日期、航线类型查询') without adding new semantic detail beyond the schema. It does not, for example, clarify airport code format or route-type mapping beyond what the schema already says.

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 '指定机场核心运行指标' and then lists the exact metrics returned: daily planned/actual flights, punctuality rate, execution rate, half-hour flight waves, and airline/aircraft departure volumes. It is clearly differentiated from the sibling 'dast_airline_operation_statistics' by being airport-scoped rather than airline-scoped.

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 implies the tool should be used for airport-level operational reporting and states the query inputs ('按机场、开始日期、结束日期、航线类型查询'). It does not explicitly name alternatives or exclusions, but the airport scope and metric list give clear context for when this tool applies.

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 and delivers strong contextual constraints: date window, required preconditions, and a detailed exclusion list. It does not disclose the response format or probability units, but for a read-only prediction query this is a minor omission.

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 dense but purposeful: every sentence adds either scope, constraints, or alternatives. It could be lightly restructured for scannability, but there is no redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is sufficiently complete for an agent to decide when to call the tool, what parameters to require, and which scenarios belong to sibling tools. The only missing piece is a statement about the output shape or format, but no output schema exists to compensate.

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 already documents all four parameters with formats and requiredness at 100% coverage, so the description adds limited new parameter meaning. It reinforces the date window and mandatory nature of all fields, which is useful but not a substantial extension 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 names a concrete operation—querying delay and cancellation probabilities for future flights—and lists exactly which user questions it serves. It also explicitly states what it is not for, distinguishing it from real-time status, airport lists, weather, pricing, and booking 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 gives explicit when-to-use triggers such as '未来航班是否容易延误' and when-not-to-use direction, telling the agent to use the flight-number real-time status tool instead. It also instructs the agent to ask for missing required parameters and to avoid calling for out-of-range dates, leaving no ambiguity.

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 behavioral disclosure burden. It clearly indicates the tool is an information-query operation, and it discloses important behavioral boundaries: it only covers a single flight, and it explicitly excludes adjacent capabilities like future delay probability, weather, and flight trajectory. It does not explicitly state whether data is real-time or whether future dates are supported, but the field list and constraints provide strong 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 main capability is front-loaded in the first sentence. The rest is structured logically: use cases, date-fallback behavior, and explicit exclusions. The field list is long but serves the purpose of disambiguating scope from siblings; it could be tightened slightly, but it is not 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?

With no output schema, the description carries the burden of explaining what the tool returns and does. It enumerates the relevant result categories (status, schedules, airports, terminals, gates, baggage, flight duration, etc.), covers the required parameters, addresses the missing-date ambiguity, and explicitly carved out sibling-tool domains. For a low-complexity tool with two scalar parameters, this is complete enough for an agent to select and call 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 coverage is 100%, so the baseline is 3. The description adds operational value beyond the schema: it explains what to do when the user does not provide a date ('应先追问日期，或在业务允许时明确按当天查询'), effectively giving the agent a policy for handling the required date parameter. It also reinforces that the flight number and date are the core query keys.

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: query a single flight's dynamic information by flight number and date. It then lists concrete use cases (status, departure/arrival, delays, gates, baggage, etc.) and explicitly states what it is NOT for (flight lists, ticket pricing, booking, future delay probability, airport weather, flight path), which clearly separates it from sibling 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?

The description explicitly says when to use the tool ('适用于用户询问某个具体航班...') and when not to use it ('该能力不用于查询某条航线的航班列表、机票价格、余票、订票、退改签、...'). It also gives concrete guidance for missing date: first ask the user for the date, or clearly treat it as today if business rules allow.

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 full behavioral disclosure burden. It clearly states that the tool returns all cabin data when cabin is omitted and only the specified cabin when provided, and that a date is mandatory. It also implies read-only behavior by describing a query operation. However, it does not explicitly mention idempotence, rate limits, or potential error states, which would be useful but are not critical for a simple query tool.

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 paragraph but efficiently front-loads the core purpose and lists key fields. It then provides usage scenarios and exclusions in a logical order. While it is somewhat long, each sentence adds necessary information; it could be structured with bullet points for readability, but it remains clear and avoids fluff.

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 complexity (oneOf logic, 5 parameters, no output schema), the description covers the essential context: what data is returned, how to handle missing date, cabin behavior, and exclusions. It does not mention error handling or edge cases like no results, but the coverage of invocation rules is strong. For a query tool with no output schema, this is sufficiently 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?

Schema coverage is 100%, so all parameters are documented. The description adds value beyond the schema by explaining the alternative query modes (fnum OR depCode+arrCode), the optional cabin behavior (defaults to all cabins), and the rule to ask for date if missing. This contextual guidance helps the agent select the correct parameters for the user's intent, going beyond the bare schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool queries flight comfort information by flight number and date, enumerates the returned fields (seat width, pitch, recline, entertainment, power, Wi-Fi, meals, aircraft age, punctuality, baggage allowances, cabin class, etc.), and clarifies its applicability to user questions about ride experience, seat comfort, onboard services, and baggage. It also explicitly lists what it is NOT for (real-time status, airport flight lists, ticket prices, etc.), clearly distinguishing it from sibling tools like dast_flight_dynamic and dast_future_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 provides explicit when-to-use scenarios (user asks about comfort, seats, services, baggage, aircraft age, cabin comfort) and when-not-to-use (real-time status, pricing, weather, flight path, etc.). It also gives concrete instructions: ask for date if missing, omit cabin if unspecified (returning all cabins), and query only the specified cabin if given. This fully guides an agent on invocation conditions without ambiguity.

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 behavioral burden and does so thoroughly: it discloses that the tool is paid, that repeated calls should be avoided, that the returned file_url is short-lived and must be downloaded/parsed immediately, and that empty or zero metrics must not be fabricated. This goes well beyond the 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?

The description is compact and front-loaded: purpose first, then usage rule, then exclusions, then data caveats. Each paragraph conveys a distinct decision-relevant fact with no filler, so 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?

Even though there is no output schema and no annotations, the description tells the agent what to expect (xlsx, contents, file_url), how to handle the result (download/parse immediately, don't repeat), and which claims are safe to make (only return actual metrics). This is complete enough for correct invocation and response handling.

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 schema already documents date as required with format, range, and failure behavior. The description repeats the required format and adds the confirmation rule, but does not add substantial semantic detail beyond the schema, so 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?

The description uses a specific verb and resource ('生成...全国民航每日总览 Excel 文件') and enumerates the workbook worksheets, so an agent knows exactly what the tool produces. It also excludes adjacent query types (single flight dynamics, airport weather, flight paths, routes, delay probability), differentiating it from its 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?

It states explicit conditions for use ('适用于用户要求查看、下载或分析某一天的全国民航运行情况') and clear negative guidance ('若查询单个航班动态...不使用本工具'). It also instructs the agent to confirm the date when not provided, which is actionable and prevents misinvocation.

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 full behavioral disclosure. It is transparent about the returned data (position, speed, altitude, heading, aircraft, status, scheduled times) and the precondition that departure/arrival/date must be complete. It does not mention failure behavior, data freshness, or source reliability, which prevents 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?

The description is long but each sentence carries distinct guidance: output fields, trigger intents, missing-parameter handling, sibling routing, and exclusions. It is front-loaded with the main purpose and output list; the length is justified by the tool's need to disambiguate many flight-related intents.

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 4-parameter read-only flight lookup with no output schema and no annotations, the description covers inputs, output fields, when to use, alternatives, and exclusions. An agent has enough information to decide to call it, assemble parameters, and anticipate the returned information.

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 each parameter already has type, format, and example. The description adds no meaning per parameter beyond reinforcing that all four are required; the missing-parameter guidance is useful usage context but not new parameter semantics, 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 opens with a specific verb ('查询') and a precise resource ('航班飞行轨迹及当前位置相关信息'), then enumerates the exact fields returned. It also distinguishes itself from nearby tools by listing what it is not for (airport flight lists, comfort, delay probability, weather, pricing, booking), so an agent can tell it apart from 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?

It states explicit trigger scenarios (`用户询问某个航班现在飞到哪里、实时位置、经纬度、高度、速度、航向、航迹`), prescribes behavior when required segments are missing (`应先追问或由系统补齐`), and routes other intents like gates, terminals, check-in, baggage, times, and status to a different flight-number query tool. A negative list further prevents misuse.

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. It discloses scope boundaries and the multi-airport behavior, but does not explicitly state read-only semantics, response format, or any data freshness/availability caveats. For a query tool this is adequate but not rich.

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 efficiently structured: main capability first, then usage scenarios, then conversion rules, then exclusions. Every sentence carries useful decision information and there is no 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 three-parameter list-query tool with full schema coverage and no output schema, the description is nearly complete. It covers input conversion, multi-airport ambiguity, typical user intents, and exclusions. It does not describe the output structure, but the relevant fields are implied by the usage examples.

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 schema already documents all three parameters with formats and examples. The description adds value by explaining how city names should be converted to depCode/arrCode and how to handle cities with multiple airports, which goes 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?

Description states a specific verb and resource: querying an airport-pair flight list by departure, arrival, and date. It distinguishes itself from siblings by explicitly listing what it is not for, such as real-time status, prices, booking, weather, and flight paths.

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 when-to-use guidance with concrete user query examples, plus a conversion rule for city names to airport codes and a multi-airport handling policy. It also names exclusions that route the agent away from sibling tools.

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 behavioral disclosure burden. It clearly describes query behavior, the weather dimensions returned, and even flight-impact assessment, while ruling out non-covered areas. It does not mention data source, forecast horizon, or response format, but the stated boundaries are strong and non-contradictory.

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 compact sentences, each earning its place: purpose and scope, parameter normalization rules, and explicit negative scope. The most important information is front-loaded, with no filler or redundant restatement.

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 weather query tool with no output schema, this description is sufficiently complete. It covers when to use, how to prepare the parameter, how to resolve ambiguity, what data will be returned, and which scenarios are out of scope.

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 required 'airport' parameter is already documented. The description adds meaningful semantic guidance beyond the schema by explaining how to map user-provided airport/city names to the three-letter code and how to handle cities with multiple airports.

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: '根据机场三字码查询机场未来天气信息'. It enumerates the exact weather attributes covered and explicitly excludes flight-dynamic, delay, ticket, and booking concerns, making it clearly distinguishable from the listed sibling 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 states when to use the tool, including user intent examples, and provides concrete conversion rules from airport/city names to the required IATA code. It also explains the multi-airport ambiguity handling and explicitly lists what the tool is NOT for, which is excellent routing guidance.

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