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

The description adds substantial context beyond the readOnlyHint annotation by listing the exact data components returned (K-line with indicators, capital flow, history trends, northbound holdings, dividends). It does not mention potential performance costs or API call patterns, but given the annotation already signals safety, the added detail is valuable.

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 composite nature with 【复合】 and efficiently lists all included data types. No waste or 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 composite tool with no output schema, the description does a good job of enumerating the available data categories. It could potentially explain return format or pagination, but for an overview tool this level of detail is sufficient. The tool's complexity is mitigated by the clear list of contents.

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 does not add any additional meaning about the parameters (market, period, symbol) beyond what the schema already provides, so it neither enhances nor detracts from parameter understanding.

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 performs composite individual stock analysis, returning K-line with indicators (MA/MACD/KDJ/RSI/BOLL), capital flow, history trends, northbound holdings, and dividends. It uses a specific verb '一次性返回' (returns at once) and a clear resource '个股' (individual stock), distinguishing it from sibling tools that focus on single data types.

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 specifies the tool is '适合快速全面了解一只股票' (suitable for quickly and comprehensively understanding a stock), providing clear context for when to use it. It does not explicitly exclude alternatives or mention when not to use it, but the use case is well implied.

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

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

The description adds value beyond annotations by specifying the returned data types (real-time quotes, MA/MACD indicators) and the '侧併' (side-by-side) format. Since annotations already declare readOnlyHint=true and openWorldHint=false, the bar is lower. However, it does not disclose potential caveats such as data latency, maximum symbol count beyond schema, or behavior for invalid symbols.

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, well-structured sentence that conveys the tool's core value proposition upfront. It uses the '【复合】' prefix to denote composite functionality and avoids redundant filler, earning a perfect score for 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?

For a read-only comparison tool with no output schema, the description adequately covers the key return elements (real-time quotes and MA/MACD indicators). It is complete enough for an agent to select and invoke the tool. The lack of details like ordering, timezone, or error handling is a minor gap given the tool's moderate complexity, hence a 4.

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 provides descriptions for both parameters ('symbols' as stock code array 2-10, 'period' as K-line period enum). Schema description coverage is 100%, so the baseline is 3. The description adds minimal parameter-level context beyond what the schema conveys, merely hinting at 'multiple stocks' and 'recent indicators' without elaborating parameter usage.

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 explicitly states it performs multi-stock comparison analysis, returning real-time quotes and recent indicators (MA/MACD) side-by-side. The verb '返回' (returns) and resource '多只股票的实时行情和近期指标' clearly define the tool's function and distinguish it from single-stock quote/kline tools among 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 clearly conveys the context: use this tool when you need a one-time side-by-side comparison of multiple stocks with quotes and indicators. However, it does not explicitly mention alternative tools (e.g., get_kline_with_indicators for single-stock indicator analysis) or exclusion criteria, so it earns a 4 rather than a 5.

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

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

Annotations already include readOnlyHint=true and openWorldHint=true, so the safe-read behavior is covered. The description adds useful context beyond annotations: built-in concurrency control and a caution about the large data volume, which helps the agent understand operational characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one concise sentence with a clear important marker and a necessary warning. It is front-loaded with the core purpose and includes no filler. Every phrase contributes meaningful information.

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 covers key operational aspects: scope, filters, concurrency control, and data-size caution. It does not detail the return format or pagination, but the purpose is straightforward and annotations provide safety context, leaving minimal ambiguity.

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 all three parameters, so the schema already documents each parameter well. The description adds a summary-level mention of market filtering and concurrency control, but does not provide additional semantic detail beyond the schema. 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 clearly states the tool gets real-time quotes for the entire A-share market (5000+ stocks), using the specific verb '获取' (get) with an explicit resource scope. It distinguishes itself from sibling tools like get_a_share_quotes by emphasizing '全市场' (full market) and the filtering options.

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 clear context: it's for full-market real-time quotes, with market filtering and concurrency control. It also warns about large data volume. However, it does not explicitly mention alternatives or when not to use it, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, setting a safe read-only expectation. The description adds behavioral context by noting built-in concurrency control and highlighting the large data volume, which informs the agent about performance characteristics beyond the annotations.

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 front-loaded with a prominent warning marker. It communicates the essential purpose and a critical caution in just one sentence, with no wasted words or redundant content.

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?

Despite lacking an output schema, the description covers the main purpose, scope, and a key operational caution. It omits details about return format or pagination, but the tool is relatively simple with only two optional parameters, and the provided context is adequate for an agent to understand what the tool does and its risk 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?

The input schema already provides complete descriptions for both parameters (batchSize and concurrency) with defaults, achieving 100% coverage. The description's mention of '内置并发控制' only echoes this concept without adding new parameter-level detail, so it adds no significant value 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 clearly specifies the tool's function: retrieving real-time quotes for the entire Hong Kong stock market, explicitly mentioning the 2000+ stocks scope. This distinguishes it from sibling tools like get_hk_quotes (which likely targets specific stocks) and other market-specific 'get_all' variants.

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 broad market monitoring by referencing '全市场' and warns about large data volume, suggesting caution. However, it does not explicitly state when to prefer this over alternatives like get_hk_quotes or provide exclusion criteria.

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 annotations already indicating readOnlyHint=true and openWorldHint=true, the description adds useful behavioral context: '内置并发控制' (built-in concurrency control) and the size/scale warning. It doesn't contradict annotations. It could further disclose return format or batching behavior, but the caution and concurrency note add value beyond the annotations.

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: two sentences that state the core function, filter support, concurrency, and a caution. It is front-loaded with the main purpose and every clause contributes meaning. The '【重要】' marker adds emphasis 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 tool that returns a large dataset (8000+ stocks), the description covers the key points: real-time quotes, market filter, concurrency, and a volume warning. There is no output schema, but '实时行情' (real-time quotes) gives a reasonable sense of the return content. However, details like return structure, pagination, or potential limits are absent, so it's not fully complete for such a heavyweight tool.

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%; each parameter has a clear description including defaults (e.g., '每批请求的股票数量，默认 300' and '并发请求数，默认 5'). The description's mention of '按市场筛选' (filter by market) and '内置并发控制' (built-in concurrency control) only echoes schema information, adding no new semantic detail. 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 clearly states the tool's purpose: '获取全市场美股实时行情' (Get real-time quotes for the entire US stock market), with specific details like '8000+ 只股票' (8000+ stocks) and market filtering options. This distinguishes it from siblings such as get_us_quotes (single-stock quotes) and get_all_hk_quotes (Hong Kong market).

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 clear context: use this when you need full-market US quotes, with optional market filtering. It also cautions '数据量较大，请谨慎使用' (large data volume, use with caution), which implies a heavy operation. However, it doesn't explicitly name alternatives like get_us_quotes for single stocks or mention when not to use it, so it falls short of a 5.

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

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the description does not need to restate safety. It adds the context of scale ('5000+ 只') and the list of supported markets, which provides some value beyond annotations. However, it does not disclose any potential behavioral details like return format, pagination, or whether codes include exchange prefixes, which could be relevant for a list-returning 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, front-loaded sentence that conveys the core purpose and the main filter in a compact manner. Every element earns its place, with no redundant words or 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?

For a simple list-retrieval tool with two optional parameters and a clear scope, the description is adequate. It specifies that it returns a code list and supports market filtering. It does not mention the return format (e.g., just codes or with names), but '代码列表' implies codes, and the lack of an output schema makes full return-format disclosure less critical. Slight gap in describing what exactly is in the list, but overall complete for the tool's complexity.

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 both parameters ('market' and 'simple') have detailed descriptions in the schema itself. The tool description adds no extra parameter semantics beyond what the schema already provides. Baseline 3 is appropriate given the high schema coverage.

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 action and resource: '获取全部 A 股代码列表' (get all A-share code list) and explicitly differentiates from sibling tools like get_hk_code_list and get_us_code_list by specifying 'A 股' and the market filter. The verb+resource is specific and 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 provides clear context: it is for retrieving A-share code lists with optional market filtering. It does not explicitly name alternatives or state when-not-to-use, but the scope (A-shares vs HK/US/fund/industry lists) is evident from the sibling names and the description itself. It offers clear usage context without 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is clear. The description adds limited behavioral context by specifying that it returns 40+ fields of information, but it does not discuss rate limits, errors, or any special constraints beyond what annotations provide. It is consistent with annotations and adds a modest amount of value.

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, focused sentence that immediately states the core function and key return fields. No filler or redundancy. It is perfectly sized for a simple tool.

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 (one parameter, clear schema, read-only annotation), the description is nearly complete. It mentions the essential return fields (latest price, change, volume, P/E, P/B) and the resource scope (A-shares/indices). It does not enumerate all 40+ fields, but that would be excessive for the description. Minor gaps like index code format are covered by the schema example, so the description is adequate.

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 'codes' parameter has a clear description with an example (["sh600519", "sz000858"]). The tool description does not add any further semantic detail about the parameters, so the schema carries the full burden. Baseline of 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?

Description clearly states the tool fetches real-time A-share/index quotes with a specific verb ('获取') and resource ('A股/指数实时行情'). It does not explicitly distinguish from sibling tools like get_all_a_share_quotes or get_quotes_by_query, but the focus on specific codes is implied by 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?

No guidance is provided on when to use this tool versus alternatives. It does not mention that this is for specific codes rather than all A-shares, nor does it reference sibling tools like get_all_a_share_quotes or get_quotes_by_query. The usage context is only implicit from the name and schema.

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=true, covering safety. The description adds behavioral context by elaborating what each type returns (e.g., premium rate, buyer/seller business departments), but it does not disclose return format, pagination, or other constraints.

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 that states the purpose and then concisely unpacks each type. It contains no filler or redundant information.

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 three parameters and no output schema, the description adequately explains the three modes and date constraints. It could mention default behavior when dates are omitted, but overall it is sufficiently complete for selecting and invoking the tool.

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 all parameters with descriptions, but the description goes beyond by providing richer semantics for the enum values, such as specifying that detail includes premium rates and business departments. It also confirms the date applicability for specific types.

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 it retrieves block trade data and distinguishes three query modes via the type parameter. The verb '获取' (get) is specific, and the resource is unambiguous, differentiating it from sibling tools that cover other financial data.

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 explains that type determines the mode of data returned and notes that date parameters apply only to detail and daily_stat types. It does not explicitly mention when not to use this tool or name alternative tools, but the context is sufficient for a data retrieval 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 provide readOnlyHint=true and openWorldHint=true, and the description complements this by specifying that the output is a board-level summary (rather than raw stock-level data) and includes examples like sharp rises/falls. This adds useful context beyond the annotations, though it does not disclose any additional limitations or side effects (which are minimal given the read-only nature).

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 entire description is a single, compact sentence that conveys the purpose, the data grain (board-level summary), and examples of the change types. There is no redundancy or unnecessary detail, making it highly concise 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?

Given the tool has no parameters, no output schema, and simple read-only annotations, the description provides all necessary context: it specifies today's timeframe, the scope (board-level), and the nature of the data (abnormal moves summary). This is sufficient for an agent to correctly invoke and interpret the tool's 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 tool has zero parameters, and the schema coverage is trivially 100%. With no parameters, the baseline is 4, and the description appropriately avoids inventing parameter details. No further explanation is needed.

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 today's board/sector change details and returns a board-level summary (sharp rises, sharp falls, etc.). The verb '获取' (get) and the specific resource '当日板块异动详情' make the purpose unmistakable, distinguishing it from related tools like get_stock_changes.

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 the tool is for retrieving current-day board-level abnormal moves, but it does not explicitly mention when to use it over alternatives or provide exclusions. The context is clear enough for basic usage, but no explicit guidance about choosing this vs. sibling tools is given.

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 and openWorldHint, and the description adds the real-time nature and return fields. However, it does not disclose pagination behavior, default page size, or any other operational constraints beyond what annotations provide.

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, tightly-wound sentence that conveys the tool's purpose and content without any filler. It is fully front-loaded and efficient.

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 simple one-parameter schema and annotations, the description sufficiently explains the tool's output (list with latest price, change, open interest). It lacks details on pagination defaults or relationship to sibling option tools, but these are not critical for basic 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 input schema has 100% coverage with a description for the only parameter (pageSize), so the description adds no extra semantic value. The description does not mention pagination or provide any context 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 clearly states the tool retrieves real-time CFFEX option quotes (stock index options) and lists included fields like latest price, change, and open interest. It distinguishes itself through the '中金所' (CFFEX) reference, though it does not explicitly compare with overlapping sibling tools like get_index_option_spot.

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 when real-time CFFEX stock index option quotes are needed, but it provides no explicit context, exclusions, or alternatives. No guidance is given on when to prefer this tool over similar option quote 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?

The description adds no behavioral context beyond the readOnlyHint annotation. It does not mention pagination, return structure, data units, or any limitations. Since annotations already declare the safety profile, the description fails to contribute additional transparency about how the tool behaves.

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 no redundancy. It concisely captures the tool's core function without extraneous words, fitting the simple nature of the tool.

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 and minimal description, the agent lacks essential context about what data is returned and how to interpret it. The tool is simple, but the description does not compensate for missing output structure, leaving the completion incomplete.

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 parameters documented (symbol enum with Chinese labels, pageSize as '每页数量'). The description provides no additional parameter meaning beyond the schema, so the baseline score of 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 '获取 COMEX 黄金/白银库存数据' clearly specifies the action (获取) and the resource (COMEX gold/silver inventory). It distinguishes from sibling tools like get_futures_inventory by focusing on the COMEX exchange and specific commodities (gold/silver).

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 guidance is provided on when to use this tool versus alternatives such as get_futures_inventory or get_futures_inventory_symbols. The description only states what it does, leaving the agent to infer suitability without explicit context 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?

The description adds the behavioral detail that data is daily ('日 K 线'), which is not fully captured by the tool name alone. However, it omits other behavioral traits such as return format, pagination, or any limitations. Given the readOnlyHint annotation already establishes this as a read-only operation, the added context is modest but acceptable.

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, clear sentence that immediately conveys the tool's purpose. It is appropriately sized with no wasted words or redundant phrases.

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 low complexity (one parameter, no nested objects, no output schema), the description is mostly sufficient. It does not explain the return value structure, but the name and description strongly imply K-line data, and the schema example clarifies the symbol format. The lack of usage guidance is the main gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the single parameter 'symbol' completely, including an example format. The description adds no additional parameter semantics beyond what the schema already provides, 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?

The description clearly states the tool's function: getting daily K-line data for commodity option contracts. It uses a specific verb ('获取') and a specific resource ('商品期权合约日 K 线'), which effectively distinguishes it from sibling tools like index option K-line or futures K-line.

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 exclusions, prerequisites, or alternative tools. Users are left to infer usage solely from the tool name and the short description.

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 readOnlyHint annotation already indicates it's a safe read operation. The description adds the T-quote structure and real-time nature, which is useful but not extensive behavioral detail beyond the annotation.

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 concise sentence that front-loads the primary action and result, with no redundant words.

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 spot quote tool with a read-only annotation and clear return description ('returns real-time quotes for each strike'), the description is sufficient despite lacking an output schema.

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 provides full descriptions for both parameters (variety and contract). The tool description does not add additional param semantics, so it meets the baseline for high schema coverage.

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 it retrieves commodity option T-quotes (call/put) with real-time data for each strike price, which distinguishes it from sibling tools like get_commodity_option_kline and get_index_option_spot.

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 its use for commodity option spot quotes, but it does not explicitly mention when not to use it or suggest alternatives such as get_index_option_spot for index options.

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 provide readOnlyHint=true and openWorldHint=true. The description adds that the tool returns real-time quotes for all stocks in the sector, which is useful behavioral context beyond the safety/static hints. No contradictions with annotations.

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 that precisely conveys the purpose and output. There is no redundant or filler content.

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 tool with one parameter, no output schema, and clear annotations, the description is complete: it states the action, the input type, and the result. No additional context seems necessary for an AI agent 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%, and the parameter description in the schema clearly explains that symbol can be a concept name or code. The tool description does not add extra parameter semantics beyond what the schema already provides, so the baseline of 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 clearly states the tool's action (获取/获取列表) and resource (概念板块成分股列表), and even indicates the return content (实时行情). This distinguishes it from siblings like get_industry_constituents (industry vs concept) and get_concept_list (list of concepts vs constituents).

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 is for retrieving concept sector constituents, which provides context for when to use it. However, it does not explicitly mention alternatives or exclusions, such as 'use get_industry_constituents for industry sectors.'

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=true, and the description adds no behavioral context beyond this. It doesn't disclose date-range defaults, response format, or handling of invalid symbols, so it provides no new information beyond annotations and 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 a single, concise sentence that front-loads the main purpose and includes only essential information.

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 moderate complexity (5 params, enums, no output schema), the description is minimal. It provides no guidance on usage context or output expectations, though the schema covers parameter details thoroughly.

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 description needn't repeat parameter details. The mention of 'daily/weekly/monthly' and 'adjustment' is redundant with schema enums; it adds no additional semantics.

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 historical K-line data for concept sectors, specifying period types and adjustment support. It distinguishes itself from sibling tools by naming 'concept sector' as the resource, though it doesn't explicitly reference alternatives.

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 guidance is provided on when to use this tool versus sibling K-line tools like get_industry_kline or get_concept_minute_kline. There are no prerequisites, exclusions, or context about data availability.

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=true and openWorldHint=true, so the agent knows it's a safe read operation. The description adds the specific return fields (name, code, change%, leader stock), but does not disclose additional behaviors such as ordering, pagination, or data freshness. Since annotations cover the safety profile, this is acceptable.

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?

Single sentence that directly states purpose and return fields. No filler or 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 zero-parameter list tool with no output schema, the description sufficiently covers what data is returned and the scope (all concept sectors). It could be more exhaustive about exact fields (uses '等'), but it is adequate for an agent to invoke 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 tool has zero parameters, so the description cannot add parameter meaning. Per rubric, baseline 4 applies, and the description's mention of return fields is the only relevant context.

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 all concept sector names and returns key fields (name, code, change%, leader stock). It uses a specific verb+resource and the '所有' (all) scope distinguishes it from sibling tools like get_concept_spot or get_concept_constituents which focus on specific concepts.

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 obtaining the full list of concept sectors, but it does not explicitly specify when to use this tool versus alternatives like get_concept_spot or get_concept_constituents. No exclusions or alternative names are mentioned.

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

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

Annotations declare readOnlyHint: true, so the read-only nature is already known. The description adds the minute/intraday scoping but no further behavioral details such as return format, time coverage, or rate limits. With annotations covering safety, a neutral score is appropriate.

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 conveys the essential purpose without redundant details. Every word contributes meaning, making it highly concise.

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 tool is simple and read-only, with no output schema. The description, combined with the schema and annotations, sufficiently explains what the tool does for a straightforward data retrieval. Some details like return layout or historical depth are absent, but the overall context is adequate.

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 describes both parameters (symbol and period) with enums and descriptions. The description adds minimal information beyond schema, so it does not meaningfully enhance parameter understanding. Baseline 3 is applied due to high schema coverage.

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 action ('获取') and resource ('概念板块分钟 K 线/分时数据'), distinguishing it from sibling tools like get_industry_minute_kline and get_minute_kline. It is specific and 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 implies use for concept sector minute data, providing clear context. However, it does not explicitly state when to use this tool over alternatives like get_concept_kline (daily) or get_industry_minute_kline, so it lacks explicit 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?

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds that it returns '详细指标' (detailed indicators), but it does not specify what those indicators are or any additional behavioral traits such as output format or error handling. This is adequate but not richly 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 a single, direct sentence that clearly states the action and outcome. It is front-loaded and contains no unnecessary words, making it highly efficient for an agent to parse.

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 should clarify what '详细指标' includes to help the agent anticipate the return value. It is vague on the actual fields (e.g., price, change, volume). The tool is simple with one well-documented parameter, so the gap is moderate.

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 description for the sole parameter 'symbol' is complete, explaining it accepts a concept sector name or code with examples. The tool description does not add further parameter-level detail, but with 100% schema coverage, no additional compensation is needed.

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 retrieves real-time quotes for concept sectors and returns detailed indicators. This clearly distinguishes it from sibling tools like get_concept_list (listing sectors), get_concept_constituents (constituent stocks), and get_concept_kline (historical candles).

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 use for current concept sector market data via the term '实时行情', but it does not explicitly state when to prefer this tool over alternatives like kline or minute-kline tools. No exclusions or alternatives are 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?

Annotations already declare readOnlyHint=true, and the description adds value by enumerating the types of information included (cash dividends, share transfers, ex-rights date, payment date, and '20+ dimensions'), giving the agent a clearer expectation of the return content without contradicting the annotations.

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 that packs essential information: the resource, key content dimensions, and a sense of comprehensiveness. No filler or 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?

With no output schema, the description compensates by naming several specific data fields and indicating '20+ dimensions'. This gives a solid sense of what to expect. It doesn't list every field, but it is sufficient for a single-param read-only tool.

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 description covers the symbol parameter fully with examples. The tool description does not add extra parameter-level semantics, but since coverage is 100%, the baseline of 3 is appropriate; the description's mention of dimensions is about the return value, not the parameter.

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 stock dividend distribution details and specifies key dimensions (cash dividends, share transfers, ex-rights date, payment date). This is a specific verb+resource that distinguishes it from all sibling tools, none of which mention dividend data.

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 dividend details for a given stock symbol. It doesn't explicitly name alternatives or exclusions, but given the sibling tools are all quotes/kline/fund flow tools, the context is clear enough for an agent to select this tool when dividend information is requested.

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=true, so the read-only nature is covered. The description adds the return fields (上榜个股, 上榜原因, 买入/卖出总额), which is useful context, but does not disclose any additional behavioral traits such as pagination, ordering, or limits. No contradiction with annotations.

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 a clear verb and resource, followed by the relevant scope and return details. Every phrase carries information and there is zero waste.

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 2-parameter, read-only list tool with good annotations, the description is mostly complete: it explains the purpose, date range, and return content. However, since there is no output schema, a brief note on return format or potential limitations (e.g., result limits) would be beneficial. Minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: both startDate and endDate have clear descriptions with format examples. The description's '按日期范围' only restates what the schema already conveys, adding no extra meaning beyond the structured parameter info.

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 starts with a specific verb '获取' (get) and resource '龙虎榜详情列表' (Dragon-Tiger list details), scoped by date range '按日期范围'. It also lists the returned contents (listed stocks, reasons, buy/sell totals), which clearly distinguishes it from sibling tools like get_dragon_tiger_stats (stats) and get_dragon_tiger_seat_detail (seat details).

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 date range scoping implies when to use it, but there is no explicit guidance on when to choose this tool over its siblings (e.g., get_dragon_tiger_stats, get_dragon_tiger_seat_detail). No exclusions or alternative recommendations are provided, so usage guidance is only implied.

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

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

The readOnlyHint annotation is already present, and the description adds useful behavioral context: it returns combined buy/sell seat data and shows specific institutions/brokerage branches. This goes beyond the annotation, though it does not detail output format or pagination.

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 sentence, front-loaded with the main action and result. Every word earns its place; no wasted text.

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 read-only tool with two fully documented parameters and no output schema, the description sufficiently explains what data will be returned (the seat details including institutions/branches). It is complete for its complexity.

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 has 100% coverage with descriptions for both parameters (symbol and date format). The description does not add extra semantic detail beyond what the schema already provides, so the baseline score of 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 explicitly states the tool retrieves (获取) the seat details (席位明细) for a stock on a specific day (个股某日), merging buy and sell lists (买入榜+卖出榜合并). This clearly distinguishes it from sibling tools like get_dragon_tiger_list and get_dragon_tiger_stats.

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 clear context that this tool is for a single stock on a single date, implying its use case. It does not explicitly mention alternatives or exclusions, but the scope is unambiguous and the purpose is self-evident.

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=true, so safety is covered. The description adds valuable behavioral context by explaining what each statistical type computes (e.g., stock_stats = listing frequency and net buy stats) and the conditional parameter dependency. This goes beyond the schema by clarifying output semantics, although it does not mention return structure or pagination.

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 tightly packed sentences in Chinese, front-loaded with the main purpose followed by type details and a critical note. Every phrase contributes, and there is no redundancy or 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 moderate complexity with conditional parameter dependencies, the description covers the essential distinctions and requirements. No output schema exists, so the description could have mentioned return format details, but it still provides enough context for an agent to invoke the tool correctly. It feels nearly complete but leaves some ambiguity about the output structure.

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 enriches parameter understanding by providing more specific meanings for type values (e.g., stock_stats = 个股上榜频次和净买入统计 vs schema's simpler 个股上榜统计) and clarifies the period/date distinction. This adds value beyond the schema descriptions.

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 Dragon-Tiger List statistical data and specifies three distinct types (stock_stats, institution, branch_rank) with concrete meanings. This differentiates it from sibling tools like get_dragon_tiger_list which likely return raw lists rather than aggregated 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?

The description provides clear within-tool usage guidance on which type to use and explicitly notes the parameter requirements: institution requires startDate/endDate, while other types use period. However, it does not explicitly mention alternatives or when not to use this tool versus sibling tools, so it falls short of a 5.

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

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

The annotations already declare readOnlyHint=true, and the description adds no extra behavioral context such as data format, pagination, rate limits, or authentication requirements. It essentially restates the tool name, offering no additional transparency beyond the structured metadata.

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 with no filler, making it efficient and front-loaded. However, it largely paraphrases the tool name, so its informational value is limited despite its compactness.

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, read-only data retrieval tool with no output schema, the description gives a minimal but acceptable understanding. It lacks details about return structure or how to obtain valid option codes, making it adequate but not comprehensive.

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 describes the single parameter 'code' with 100% coverage, so the baseline is met. The description does not add further detail about code format or how to find valid codes, but the schema already carries the essential 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 '获取 ETF 期权合约日 K 线数据' clearly states the action (get) and resource (ETF option daily K-line), distinguishing it from sibling tools like get_index_option_kline or get_etf_option_minute by specifying 'ETF 期权' and '日 K 线'.

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 by the resource type, but the description provides no explicit guidance on when to use this tool versus alternatives like get_index_option_kline or get_history_kline. No exclusions or alternative recommendations are given.

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 annotation readOnlyHint=true already signals a safe read operation. The description adds value by disclosing the output fields (expiration date and remaining days), even though it says '等信息' (etc.) without specifying the complete return structure. This is useful context for an agent and does not contradict the annotations.

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 sentence, front-loaded with the action and resource, and contains no redundant words. Every part contributes to understanding the tool's 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?

This is a simple read-only tool with two well-documented parameters. The description covers the primary return fields but leaves some ambiguity about the exact return type/format and the precise meaning of 'expire day' (e.g., last trading day vs first day of expiry period). Given the lack of an output schema, a bit more detail would improve completeness, but it is adequate for the tool's simplicity.

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%: both 'cate' and 'month' have explicit descriptions. The tool description does not add meaning beyond the schema, such as the relationship between parameters or expected formats, so the baseline score of 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 clearly states the action ('获取' = get) and resource ('ETF 期权到期日信息' = ETF option expiration date information), and specifies the output contents (到期日, 剩余天数). This distinguishes it from sibling tools like get_etf_option_months, which likely return the list of available months rather than the expiration details for a specific month.

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 from its purpose but provides no explicit guidance on when to use this tool vs alternatives. Sibling tools such as get_etf_option_months or get_etf_option_daily_kline exist, but the description does not mention them or explain the distinction. It is not misleading, but it lacks clear when-to-use/when-not-to-use context.

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=true, and the description merely restates that the tool 'gets' data without adding new behavioral context. It does not disclose any limitations, return format details, or special behavior beyond what the annotation implies, providing no added transparency value.

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, efficient sentence that conveys the core purpose without wordiness. It appropriately front-loads the key information, although it could be expanded slightly with usage context without losing 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?

For a simple single-parameter read-only tool, the description provides the essential purpose. However, with no output schema, it fails to specify what data the response contains (e.g., price points, volume, timestamps), leaving gaps in the user's understanding of what '分钟走势数据' includes.

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 the single parameter 'code' already described as 'ETF 期权合约代码'. The description adds no additional parameter meaning or usage hints, so it meets the baseline but does not enhance understanding of the parameter 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 '获取 ETF 期权合约分钟走势数据' clearly states the action (获取/get) and resource (ETF option contract minute trend data), making the tool's purpose unambiguous. However, it does not explicitly differentiate from sibling tools like get_etf_option_daily_kline, relying on the obvious distinction between minute and daily data.

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 offers no guidance on when to use this tool versus alternatives. There is no mention of prerequisites, typical use cases, or exclusions such as "use get_etf_option_daily_kline for daily data" or "this tool only returns today's minute data."

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=true, so no safety ambiguity exists. The description adds the output type (list of months) but does not disclose format, sorting, or any other behavioral characteristics beyond what is implied by the annotation.

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 that directly conveys the tool's purpose. No unnecessary words 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?

This is a simple read-only tool with one documented enum parameter, and the description adequately states the return type (contract months list). However, since there is no output schema, it would benefit from specifying the expected format (e.g., YYYYMM strings) or clarifying how it differs from the similarly named get_etf_option_expire_day.

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 the enum and description for the single parameter 'cate' fully explaining its allowed values. The tool description adds no additional meaning to the parameter, which aligns with the baseline of 3.

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 action ('获取') and the resource ('ETF 期权可用合约月份列表'), specifying the result as a list of contract months. It does not explicitly distinguish itself from nearby sibling tools like get_etf_option_expire_day, but the '月份' (months) wording is clear enough.

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 guidance is given about when to use this tool versus alternatives. While the description implies it is for retrieving ETF option contract months, it does not mention exclusions, prerequisites, or relationships to sibling tools such as get_etf_option_expire_day or get_etf_option_daily_kline.

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=true and openWorldHint=true, indicating a safe read operation. The description adds useful context about the scope ('全部' = all) and scale ('26000+'), but does not disclose additional behavioral traits such as response format, potential pagination, or size implications. It does not contradict annotations.

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 that immediately communicates the tool's purpose and scope. It avoids unnecessary detail and is well-structured for quick comprehension.

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 list retrieval tool, the description adequately conveys what the tool does and its scale. It does not describe the exact return structure, but since there is no output schema and the name implies a list of codes, the description is sufficiently complete for this simple tool.

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, and schema coverage is 100% (vacuously). Per the rubric, 0 params yields a baseline of 4. The description adds no parameter information because none exists to describe, which 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 '获取全部基金代码列表' clearly states the action (get all fund codes) and the resource (fund code list), distinguishing it from sibling tools like get_a_share_code_list or get_hk_code_list. It also provides a specific count (26000+ 只), which adds specificity and scope.

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: this tool is for retrieving the full list of fund codes. However, it does not explicitly mention when to use it versus alternatives (e.g., stock or HK code lists), nor does it state any exclusions. The usage is self-evident from the name and description, but lacks explicit comparative 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?

readOnlyHint=true already covers safety; the description adds what data is returned (main/retail inflows/outflows, net inflow ratio). It does not disclose data freshness, exact units, or edge-case behavior, but the added return detail is 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?

One concise sentence, front-loaded with the core action, and no filler. Every part of the description adds informational value.

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 tool with one documented parameter, readOnly annotation, and no output schema, the description adequately states the operation and return content. It could be slightly more explicit about being current (not historical) flow, but is otherwise 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?

The schema covers 100% of parameter semantics with description and example for 'codes'. The tool description adds no additional parameter meaning, so 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 the specific verb '获取' (get) and resource '股票资金流向' (stock capital flow), and clearly states that it returns main/retail inflow/outflow amounts and net inflow ratio. This distinguishes it from market-level or ranking siblings like get_market_fund_flow and get_fund_flow_rank, though it doesn't explicitly name them.

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 usage context is implied: call this when you need fund flow for specific stock codes. However, there is no explicit when-to-use/when-not-to-use guidance, and it doesn't differentiate from get_stock_fund_flow_history or other fund-flow 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 readOnlyHint=true, the safe-read nature is already covered by annotations. The description adds that stock rankings return '全市场主力净流入 TOP' and sector rankings return industry/concept/region lists, which gives some context about the data scope. However, it does not disclose ordering behavior, result limits, or any other nuances beyond the annotations.

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 concise sentences, front-loaded with the core purpose and then detailing the two modes. Every sentence contributes meaning, with no redundancy or 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 there is no output schema, the description should clarify the return structure more thoroughly. It says stock rankings return TOP main net inflows and sector rankings return ranking lists, but it does not specify whether the result includes stock codes, names, values, or the number of results. This leaves some ambiguity for an agent expecting to parse the response.

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 three parameters (scope, indicator, sectorType) have descriptions in the schema. The tool description adds minimal extra meaning, mostly confirming the role of scope and the sector types, which are already enumerated in the schema. It does not provide additional parameter-level context beyond what the schema offers.

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 function: '获取资金流排名' (get fund flow ranking) and distinguishes between stock and sector rankings via the 'scope' parameter. It also describes what each mode returns (full-market top main net inflows for stocks; industry/concept/region rankings for sectors), differentiating it from sibling tools like get_fund_flow and get_market_fund_flow.

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 by explaining what the tool does, but it does not explicitly state when to use this tool vs alternatives such as get_stock_fund_flow_history or get_sector_fund_flow_history. There is no mention of exclusions or preferred scenarios, leaving the agent to infer that this is for ranking rather than detailed historical flow analysis.

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 provide readOnlyHint=true, and the description complements this by specifying the returned data: latest NAV, cumulative NAV, and change amount. It does not disclose error handling or rate limits, but for a simple read-only quote tool, this is adequate. No contradiction with annotations.

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 sentence that immediately states the action and resource, then lists key output fields. It is front-loaded and contains no filler or redundant information.

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 (one parameter, read-only, no output schema), the description covers the essential purpose and return values. The annotations and schema cover safety and input format. Even without explicit error/limit details, it is sufficiently complete for an agent to use 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 the single 'codes' parameter with an example, so schema coverage is high (100%). The tool description does not add further parameter-level detail beyond the schema, so 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 clearly states '获取公募基金实时行情' (get public fund real-time quotes), specifying both the action and the resource. It distinguishes from sibling quote tools by focusing on public funds and mentions return fields, making the purpose 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 implies usage for public fund quotes but does not explicitly compare with alternatives like get_a_share_quotes or get_quotes_by_query. There is no when-not-to-use guidance, so the guideline is inferred from the tool name and description rather than stated.

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 indicate readOnlyHint=true, so the read-only nature is known. The description adds that it returns historical changes (time series) and uses a given symbol, which is helpful context. However, it does not disclose pagination behavior, default date range, or response format, so it provides only modest value beyond annotations.

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, succinct sentence that front-loads the tool's purpose and output. No filler or redundancy, making it easy to parse quickly.

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 read-only data retrieval tool with three well-documented parameters and no output schema, the description and schema together provide sufficient context. It lacks detail on return structure or edge cases, but given the simplicity and annotations, it is adequately 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% for all three parameters (symbol, pageSize, startDate), so the schema fully documents parameter meanings and format. The description adds no additional parameter-level semantics beyond what the schema already provides, earning the baseline score.

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 ('获取' - get) and resource ('期货仓单/库存数据' - futures warehouse receipt/inventory data), clearly distinguishing it from sibling tools like get_futures_kline (price data) and get_futures_inventory_symbols (symbol list). It states the output as historical inventory changes for a specified variety.

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 clear context: use this when you need historical inventory/warehouse receipt changes for a commodity. It does not explicitly name alternatives or exclusion criteria, but the purpose is obvious and the schema references get_futures_inventory_symbols for symbol acquisition, aiding correct 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the output is a list of variety codes, but it does not disclose additional behaviors such as response format, whether the list is exhaustive, or any rate limits. No contradiction with annotations.

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 front-loads the action ('获取') and resource, making it immediately scannable and efficient.

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

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

For a zero-parameter list tool with no output schema, the description sufficiently conveys the return value (all queryable inventory codes). Minor improvement would be mentioning how this integrates with get_futures_inventory, but the current description is adequate for the tool's simplicity.

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 there is nothing for the description to explain. Baseline for no-parameter tools is 4, and the description correctly omits parameter details.

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 it retrieves a list of futures warehouse receipt/inventory symbols and returns all variety codes with queryable inventory. This clearly distinguishes it from related tools like get_futures_inventory, which would return actual inventory data for specified symbols.

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 context is implied but not explicit. The description suggests this tool provides available inventory symbols, but it does not explicitly state 'use this before get_futures_inventory' or mention any alternatives/exclusions. No direct when-to-use guidance is provided.

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

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

Annotations declare readOnlyHint=true, and the description adds context about the included data fields (OHLC, volume, open interest) and period options, providing value beyond the structured annotations without contradicting them.

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 sentence with essential information front-loaded, containing no redundant words.

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

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

For a read-only K-line retrieval tool with fully documented parameters and annotations, the description covers the key output fields and period options, though it doesn't describe return structure or edge cases.

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% with each parameter described, so the description adds no additional parameter semantics beyond what the schema already provides.

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 domestic futures historical K-line data with specific periods (daily/weekly/monthly), distinguishing it from global futures and minute-level K-line 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 implies usage for domestic futures historical K-line but doesn't explicitly name alternatives or exclusion criteria, so it relies on the agent to infer context 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?

The description is consistent with the readOnlyHint annotation, but it adds no behavioral information beyond what the schema already provides. It does not mention pagination, default date ranges, output format, or any special constraints, so the annotation carries most of the safety and behavior signaling burden.

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 Chinese sentence with no wasted words or redundancy. It is appropriately concise for its core purpose, though it could have used the space to add distinguishing guidance or behavioral details.

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?

While the K-line concept is generally well understood, the description does not explain the return format, default behavior when startDate/endDate are omitted, or how this tool differs from other kline tools. Given no output schema, a bit more detail would make it complete, but the core data type and parameters are sufficiently clear to be minimally viable.

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 100% coverage, including the period enum and date format examples. The description only repeats the period values ('日/周/月') already in the schema, adding no new semantic meaning beyond the structured 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 the action ('获取' / get) and the resource ('全球期货历史K线数据' / global futures historical K-line data), with the period scope noted in parentheses. It is specific enough to identify the tool's purpose, but it does not explicitly distinguish it from the closely named sibling get_futures_kline or get_global_futures_spot.

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 guidance is provided about when to use this tool versus alternatives. There is no mention of when to prefer this over get_futures_kline or get_global_futures_spot, and no exclusions or prerequisites are stated. The usage context is only implied by the tool's name and generic description.

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 provide readOnlyHint and openWorldHint. The description adds the scope of 'global major futures products' (not all contracts), which is useful context, but it does not disclose pagination behavior or return format.

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 one sentence and front-loaded with the action. It is slightly redundant in using both '获取' and '返回' but remains efficient and clear.

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 tool with one optional parameter and no output schema, the description provides sufficient context to identify the tool's purpose and invocation. However, it lacks return field details, which is acceptable given the tool's simplicity.

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% for the single pageSize parameter, which is fully described in the schema. The description adds no additional parameter semantics beyond what the schema provides.

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 it retrieves real-time global futures quotes for major products like crude oil, gold, and copper. It distinguishes from sibling tools like get_global_futures_kline by specifying 'spot' market data.

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 by the description ('获取全球期货实时行情'), but there are no explicit when-to-use or alternative tool guidance. It does not mention when to prefer this over get_global_futures_kline or get_futures_kline.

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 readOnlyHint annotation covers safety, and the description adds useful output content (fields included). It does not disclose pagination, default date ranges, or rate limits, but for a read-only data retrieval tool, the added return-field info justifies a moderate-to-high score.

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 that front-loads the action ('获取') and includes the market, data type, periods, and key fields without redundancy. Every element is informative.

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 5-param schema with full documentation and readOnly annotation, the description sufficiently orients an AI agent. It could mention default date ranges or that parameters are optional, but the core functionality is clear. A 4 reflects the minor gap in behavioral defaults.

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 provides 100% coverage of all five parameters with descriptions and enums, so the description's mention of periods (daily/weekly/monthly) adds no new meaning. Baseline 3 is appropriate as the schema handles parameter documentation.

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 A-share historical K-line data with specific timeframes (daily/weekly/monthly) and included fields (OHLC, volume, change %). This specific verb+resource phrasing distinguishes it from sibling tools for HK/US history K-lines and minute-level data.

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 A-share historical K-line data in daily/weekly/monthly periods but does not explicitly mention alternatives such as get_us_history_kline or get_minute_kline. The market qualifier 'A股' provides clear context, but no exclusions or alternative tool references are given.

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=true, so the safe-read nature is known. The description adds the scale of the list (2000+ 只), a useful detail beyond the annotation. However, it doesn't disclose return format or potential pagination, but this is a minor gap given the annotation coverage.

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 in Chinese that conveys the purpose and scope without any filler. Every word earns its place, and it is optimally sized for a tool with no parameters.

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 0-parameter tool with a readOnlyHint and no output schema, the description is effectively complete. It states exactly what the tool returns (the full HK code list) and even gives a count estimate, leaving no major missing 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?

The input schema has zero parameters, so the baseline is 4. The description doesn't need to explain parameter details, and there are none to clarify. This is appropriate for the tool's no-parameter interface.

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 '获取全部港股代码列表（2000+ 只）' clearly states the action (获取) and the resource (全部港股代码列表), specifying the full scope of Hong Kong stock codes. It distinguishes itself from sibling tools like get_all_hk_quotes (which retrieves quotes) and get_a_share_code_list (which covers A-shares).

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 its usage: when an agent needs the complete list of Hong Kong stock codes. It doesn't explicitly name alternatives or exclusions, but the context is clear and unambiguous given the sibling tool names, so the tool is easy to select correctly.

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=true and openWorldHint=false, covering the safety profile. The description adds no behavioral context beyond the resource and period types, such as output format or pagination. It does not contradict annotations.

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 that front-loads the key information (get HK historical K-line, periods). There is zero waste or 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 tool is relatively simple with one required parameter and all parameters documented in the schema. The description covers the core purpose and period choices. While there is no output schema or mention of return format, the tool name and description imply standard K-line data, so it is sufficiently complete for this 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 coverage is 100% with detailed descriptions for all 5 parameters, including enum values and defaults. The description adds no additional parameter semantics beyond the schema, so the baseline score of 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 clearly states the verb (获取/get), resource (港股历史K线/HK stock historical K-line), and scope (日/周/月 daily/weekly/monthly). This distinguishes it from sibling tools like get_us_history_kline and get_minute_kline, so the 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 implies usage for obtaining HK stock historical K-line data in daily/weekly/monthly periods, but it does not explicitly mention when to use this tool over alternatives or provide exclusions. The sibling context suggests many market-specific kline tools, but no guidance is given.

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=true, so the agent knows this is a safe read operation. The description adds the specific return fields (latest price, change percent, volume), which is useful context. However, it does not disclose any potential rate limits, error behavior, or whether the tool supports batch quotes beyond the schema's array parameter.

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 that states the core function and return fields. No wasted words or redundant information. Highly concise and 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 simple single-parameter tool with high schema coverage and read-only annotations, the description is sufficiently complete. It names the market, the type of data (real-time quotes), and the returned fields. The absence of an output schema is mitigated by the explicit listing of return fields. A minor gap is the lack of distinction from get_all_hk_quotes, but this tool clearly requires specific codes.

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 parameter description already explains the format with an example (['00700','09988']). The tool description adds no additional parameter semantics beyond the schema, so the baseline score of 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 clearly states the tool fetches Hong Kong stock real-time quotes and lists the key returned fields (latest price, change percent, volume). It distinguishes from US/A-share quote tools, but does not explicitly differentiate from sibling get_all_hk_quotes, which also covers HK quotes.

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 guidance is provided about when to use this tool versus alternatives. There is no mention of exclusions or references to sibling tools like get_all_hk_quotes or get_hk_history_kline. The agent must infer usage from the name and schema.

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=true, and the description aligns with a read operation. It adds the '日' (daily) frequency detail beyond the title but does not disclose output format, pagination, or other behavioral details. This is minimal added context over the annotations.

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 Chinese sentence, front-loaded with the core purpose ('获取指数期权合约日 K 线数据') and containing no superfluous words. It is perfectly sized for the tool's simplicity.

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 read-only one-parameter tool, the description plus schema is nearly complete. It clearly identifies the resource and frequency, but it does not explicitly differentiate from close sibling daily K-line tools like get_etf_option_daily_kline, nor describe the return shape. The standard K-line format is likely understood, so the gap is minor.

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 covers 100% of the single parameter 'symbol' with a description including an example ('io2504C3600'). The tool description adds no additional parameter semantics beyond reinforcing that the symbol is an index option contract code, so the schema does the heavy lifting.

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 the specific verb '获取' (get/retrieve) and the precise resource '指数期权合约日 K 线数据' (index option contract daily K-line data). The qualifier '指数期权' distinguishes it from sibling daily K-line tools like get_etf_option_daily_kline and get_commodity_option_kline.

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 daily K-line data of index option contracts, but provides no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives. The context is clear from the wording, but exclusions are absent.

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=true, so the safety profile is known. The description adds that it returns real-time quotes for call/put across strike prices, which is useful context, but it does not disclose additional behaviors like data formatting, sorting, or rate limits. Given the annotations, this is adequate but not exceptional.

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 that immediately states the tool's action and output. It is concise with no redundant words.

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 spot-quote tool with two well-documented parameters and a clear read-only annotation, the description adequately conveys the purpose and return content. The lack of an output schema is partially mitigated by the description's mention of T-type quotes and real-time prices, though it doesn't detail the exact fields returned.

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 covers 100% of parameter descriptions, including the product enum with specific index definitions and the contract month format with an example. The description adds no additional parameter 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 clearly states the tool retrieves index option T-type quotes (call/put) with real-time prices for each strike price. The specific verb '获取' and resource '指数期权 T 型报价' distinguish it from siblings like get_index_option_kline (historical) and get_commodity_option_spot (commodity).

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 real-time index option spot quotes, but it does not explicitly mention when to use this tool versus alternatives or provide exclusions. No guidance about kline tools or other option quote tools is given.

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=true, so the read-only nature is covered. The description adds that it returns real-time quotes for all stocks, which is useful, but doesn't disclose return structure or any pagination/rate-limit behavior.

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 sentence that immediately states the purpose and outcome. No filler words; it's front-loaded and efficient.

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 read-only tool, the description covers what it returns (real-time quotes for all constituent stocks) and the input is fully specified in the schema. However, without an output schema, the exact return fields are not disclosed, which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description for 'symbol' fully explains it accepts either an industry sector name (e.g., '小金属') or code (e.g., 'BK1027'), so the description adds no further parameter meaning. With 100% schema coverage, baseline is 3.

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 constituent list of an industry sector and returns real-time quotes for all stocks. The verb '获取' and resource '行业板块成分股列表' are specific, and the distinction from concept-sector constituents is implied by '行业'.

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 the tool is for when you need the list of stocks in an industry sector with real-time quotes, but it does not explicitly mention when not to use it or compare with alternatives like get_concept_constituents or get_industry_spot.

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 readOnlyHint annotation already indicates this is a safe read operation, so the description needs to add extra behavioral context to earn credit. It only repeats the '支持复权' (supports adjustment) feature, which is already fully documented in the schema. No additional context about return format, pagination, rate limits, or other side effects is provided.

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 that is front-loaded with the core purpose and then adds the key qualifiers (period and adjustment). Every word earns its place, with no waste or 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?

The tool is a read-only data retrieval with 100% schema coverage, but there is no output schema and no usage guidance. The description is adequate for a simple K-line fetch but does not clarify what the return data looks like or how to choose among the many sibling K-line tools. It is minimally complete but leaves noticeable 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%, with each parameter already documented in the schema. The description adds no new meaning beyond what the schema provides; it merely summarizes the period and adjust params. This matches the baseline of 3 for high schema coverage.

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 ('获取' / get), a resource ('行业板块历史 K 线数据' / industry sector historical K-line data), and the supported timeframes (日/周/月). This fully distinguishes it from minute-level and other market K-line 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?

No explicit guidance is given for when to use this tool instead of alternatives such as get_concept_kline, get_history_kline, or get_industry_minute_kline. The usage context is only implied by the name and the mention of daily/weekly/monthly periods. There are no exclusions or alternatives 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?

Annotations already declare readOnlyHint=true, so no additional safety disclosure is needed. The description adds value by specifying the returned fields (name, code, change percent, leading stock), which goes beyond the empty input schema. It does not disclose pagination or limits, but for a list endpoint this is acceptable.

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 that front-loads the purpose and includes the key return fields. Every word contributes to understanding, with no fluff or 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?

Given the low complexity (0 params) and no output schema, the description provides a fairly complete picture of what is returned. It lists the core fields and indicates there are more (etc.), which is sufficient for a simple list tool. However, it could mention ordering or size limits if any, but no strong 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?

The tool has zero parameters, so the baseline is 4. The description adds no parameter-specific information, but none is needed since the schema is empty. The description does not introduce any confusion about inputs.

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 returns a list of industry sectors with specific fields (name, code, change percentage, leading stock). It uses a specific verb and resource, but does not explicitly distinguish it from sibling tools like get_industry_spot or get_industry_constituents, though the 'list' aspect is implied.

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 the tool is used to retrieve the full list of industry sectors and their basic quote data. It provides clear context but does not mention when not to use it or suggest alternatives among the many sibling tools, leaving some ambiguity for the agent.

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 indicate readOnlyHint=true, and the description is consistent with a read operation. However, the description adds no additional behavioral context such as return format, period semantics beyond the schema, or limitations. It restates the tool's purpose without deeper disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence, front-loaded with the action and resource. It is appropriately sized for its purpose, with no unnecessary words. It lacks additional structure to convey context, but for a simple tool this is acceptable.

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 lack of an output schema and simple parameters, the description is insufficiently complete. It does not explain the expected return data, any constraints, or how this tool fits with related industry/sector tools. An agent would lack guidance on when to invoke this vs similar tools and what to expect in response.

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 both parameters (symbol, period) have descriptive Chinese descriptions, including the enum meaning for period. The description itself adds no parameter-specific detail beyond what the schema already provides, so 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 '获取行业板块分钟 K 线/分时数据' (Get industry sector minute K-line/time-sharing data) clearly specifies the verb, resource (industry sector), and data type, distinguishing it from siblings like get_industry_kline (daily/weekly) and get_concept_minute_kline (concept sector).

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 guidance is provided on when to use this tool versus alternatives. The description only defines the tool's function without mentioning related tools such as get_industry_kline or get_minute_kline, nor any exclusions or preferred scenarios.

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=true, so the agent knows this is a safe read operation. The description adds that it returns detailed indicators, but it does not specify what those indicators are, pagination behavior, or rate limits. This is adequate given the annotation coverage 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 a single, concise sentence that states the action (获取), the resource (行业板块实时行情), and the expected output (详细指标) without any wasted words. It is appropriately front-loaded and easy to parse.

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 one well-documented parameter, a read-only annotation, and a simple purpose, the description is nearly sufficient. However, the absence of an output schema and the vague reference to '详细指标' leaves the agent uncertain about the exact return structure and fields, which is a notable gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage for the single parameter, clearly describing accepted symbol formats (name or code). The tool description does not repeat or enhance this information, so it adds no extra semantic value 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 uses a specific verb '获取' (get) and identifies the resource '行业板块实时行情' (industry sector real-time quotes), clearly distinguishing it from related tools like kline, constituents, or list tools. It also states the output is '详细指标' (detailed indicators), making the tool's purpose 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 provides no guidance on when to use this tool versus the numerous sibling tools such as get_industry_minute_kline, get_industry_kline, or get_concept_spot. There are no exclusions, prerequisites, or alternative recommendations, leaving the agent to infer usage solely from the name.

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=true, so safety is covered. The description adds valuable behavioral context: it automatically fetches historical data needed for indicator calculation ('自动处理指标计算所需的历史数据'), implying extra data may be retrieved beyond the requested date range. It also states that K-line and all indicators are returned in one call, which is useful expectation-setting. No contradictions found.

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, information-dense sentence. It front-loads the key purpose with '重要', lists all included indicators in parentheses, and adds critical behavior (auto historical data handling) without any filler. Every phrase earns its place.

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

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

For a complex tool with 7 parameters, a nested object, and no output schema, the description covers the core purpose, supported markets, included indicators, and a key behavioral nuance (auto history fetching). It does not detail the response structure or what happens if the `indicators` field is omitted, but it is sufficient for initial selection and invocation. More detail on output format would push it to a 5.

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 parameters are already well-documented. The description adds semantic value by explaining that the tool supports A/HK/US markets (correlating with the `market` and `symbol` params), auto-handles history for indicators (relevant to `startDate`/`endDate`), and provides a list of configurable indicators (matching the `indicators` nested object). This goes beyond the schema's field-level descriptions.

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: '获取带技术指标的 K 线数据' (get K-line data with technical indicators), and explicitly lists MA/MACD/BOLL/KDJ/RSI/WR/BIAS/CCI/ATR. It distinguishes itself from sibling tools like get_history_kline or get_minute_kline by focusing on bundled indicators. The supported markets (A/HK/US) further clarify scope.

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 when to use the tool: when you need K-line data with multiple technical indicators in a single call, and highlights the automatic handling of historical data for indicator calculation. However, it does not explicitly name alternatives or state when not to use it (e.g., for minute-level data). Clear context, but no explicit 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only nature is covered. The description adds useful context: the distinction between account and target types, and that date defaults to the latest trading day when type=target. However, it does not disclose response format, pagination, or edge cases (e.g., behavior when date is provided for account type). 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 a single concise sentence, front-loaded with the main purpose and followed by a colon-delimited breakdown of the type parameter. Every word contributes to understanding, with no redundant or filler content. It is appropriately sized for the tool's simplicity.

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 has only two parameters, no output schema, and straightforward read-only behavior, the description covers the essential semantics: what it does, the two modes, and the optional date context. It does not describe the return structure, but for a data-retrieval tool with simple inputs, this is not a critical gap. The description is sufficiently complete for an agent to select and 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 coverage is 100%, with descriptions for both parameters. The description adds meaning beyond the schema by elaborating on what each type returns: account includes market-wide balance and trends, target includes stock-level data. This extra detail helps agents understand the semantic difference between enum values, going beyond 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 states the tool retrieves margin trading data (融资融券数据) and distinguishes between two modes: account-level statistics (全市场两融余额和融资/融券趋势) and target-level stock details (个股级别的融资融券数据). This specific verb-resource pairing and mode breakdown make it distinct from all sibling tools, none of which mention margin trading.

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 by explaining when each type is appropriate (account for market-wide trends, target for stock-level data). However, it does not explicitly mention when not to use this tool or alternatives, such as using kline tools for price data. The context is clear but lacks formal exclusions or alternative references, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that it returns inflow/outflow trends for main forces and retail, which is useful behavioral context. However, it does not disclose data granularity, time period, or any potential limitations beyond the annotations.

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 sentence that efficiently states the purpose and output. Every part earns its place: '获取大盘资金流向（上证+深证综合）' specifies target and scope, '返回主力和散户的流入流出金额趋势' specifies return value. No filler or 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?

Given the tool's low complexity (no parameters, no output schema), the description covers the essential context: what data is returned and for which market. Annotations handle safety. It could mention time frame or real-time vs. historical nature, but for a parameterless market flow tool, the description 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?

The tool has 0 parameters, so schema coverage is 100% vacuously. Per rubric, 0 params earns a baseline of 4. The description does not need to explain parameters since none exist, and the input schema is empty.

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 verb '获取' (obtain) and the specific resource '大盘资金流向' (market capital flow) with explicit scope (Shanghai + Shenzhen composite). It also describes what is returned (trend of inflow/outflow amounts for main forces and retail investors), distinguishing it from sibling tools like get_fund_flow which target individual stocks or sectors.

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 clear context: use for overall market capital flow. Though no exclusions or alternatives are explicitly named, the phrase '大盘' (whole market) implies when to choose this tool over sector/stock-specific fund flow tools. It lacks explicit 'when not to use' guidance, but the context is unambiguous.

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=true and openWorldHint=true, which covers the safety profile. The description adds valuable transparency by enumerating the composite response contents, making clear that the tool returns multiple data categories in a single call. It does not disclose potential latency or market limitations, but the added scope context is useful.

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, front-loaded with the composite label and resource name, followed by a colon-separated list of data categories. Every word earns its place; there is no fluff or 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 composite read-only tool with no output schema, the description enumerates the main data categories, giving the agent a clear expectation of the response. Minor gaps exist, such as not mentioning the includeHK parameter or historical data type, but the description is sufficiently complete for an overview tool with a simple schema.

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% for the single optional boolean parameter includeHK, which is clearly described in the schema. The tool description adds no additional parameter context, so it relies entirely on the schema. Baseline 3 applies when the schema does the heavy lifting.

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 the specific label '复合' and explicitly lists the data categories returned (major index quotes, industry/concept sector TOP10, advance/decline statistics, northbound capital, limit-up/down counts, sector anomalies). This clearly distinguishes it from sibling tools by presenting it as an aggregated overview tool.

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 as a one-shot market overview but gives no explicit guidance on when to use it over dedicated sibling tools like get_market_fund_flow or get_northbound_realtime. It does not state exclusions or name 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?

The readOnlyHint annotation already indicates this is a safe read operation. The description adds no additional behavioral context such as return format, data source, date range constraints, or adjustment behavior. It merely restates the tool's purpose and reiterates the period enum values already present in 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 a single short sentence with the key action and resource front-loaded. It is very concise, though the parenthetical period list is redundant with the schema and could be removed for even tighter phrasing. The structure is clean and scannable.

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 and a relatively simple tool, the description lacks essential context such as what the returned K-line data contains (e.g., OHLC, volume, timestamps), whether startDate/endDate are optional, and how this tool differs from the many sibling K-line tools. The absence of usage guidance and return-value details makes it incomplete for effective tool selection.

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 parameters have descriptions. The description's mention of '1/5/15/30/60 分钟' redundantly repeats the period enum, adding no new semantic meaning beyond what the schema already provides. Baseline 3 is appropriate since the schema handles parameter documentation.

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 specifies the action ('获取' / get), the resource ('A股分钟K线数据' / A-share minute K-line data), and the supported timeframes (1/5/15/30/60 minutes). It clearly identifies the tool's function and, through the 'A股' qualifier, distinguishes it from HK/US minute K-line tools, though it does not explicitly differentiate from industry or concept minute K-line variants.

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 guidance is provided on when to use this tool versus alternatives such as get_history_kline for daily data or get_industry_minute_kline for sector data. The description only states what the tool does, without any context about appropriate scenarios 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?

注解已声明 readOnlyHint=true，描述未重复安全性但补充了 market 与 stock 两个查询范围的语义差异，提供了部分上下文。未提及返回格式、分页或默认行为，但只读工具已由注解覆盖基本安全面，描述附加价值中等，符合无矛盾且有一定补充的 3 分档。

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?

描述仅用一句中文，直接点明核心功能并解释 scope 分支，信息密度高且无冗余信息，符合前载和简洁要求。

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?

工具为只读历史数据查询，schema 完整，注释说明 readOnly，描述已覆盖主用途和 scope 分支。虽未说明返回格式或与兄弟工具的区别，但结合名称和上下文足够支持调用；相较于简单工具所需的信息，描述达到基本完整，故评 4 分。

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?

输入 schema 覆盖率达 100%，所有参数在 schema 中均有完整描述（如 scope 的 enum 含义、symbol 必填条件、direction 默认方向）。描述仅概括了 scope 的分支，未提供超出 schema 的额外语义，如日期格式、方向默认值等，因此按基线评为 3。

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?

描述明确以“获取北向资金历史数据”点出动词与资源，并通过 scope 区分 market 与 stock 两种维度，与 get_northbound_realtime、get_northbound_holding_rank 等兄弟工具在名称和功能上形成清晰区分，属于具体且区分性强的目的说明。

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?

描述隐含了“历史”与“实时/排名”的使用场景差异，但未显式说明何时应使用本工具而不用备选工具，也没有列出 alternatives 或 when-not。属于依赖名称和上下文的隐含用法，未提供明确的取舍指导。

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 provide readOnlyHint=true and openWorldHint=true, so the description doesn't need to repeat safety. The description adds meaningful context by noting the default TOP 100 limit to avoid oversized responses, which is useful behavioral information. However, it does not disclose other behaviors such as return format or sorting specifics beyond what the schema implies.

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 states the core purpose, followed by a parenthetical explaining the default response limit. No wasted words; all content is directly relevant.

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

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

For a read-only ranking tool with no output schema, the description explains the purpose and default pagination but does not describe the response structure or typical fields (e.g., stock code, name, holding change). Given the tool's simplicity and the good schema coverage, it's minimally complete but leaves room for more detail on output.

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% — all four parameters have descriptions. The description's mention of 'different periods' and 'TOP 100' reinforces the period and topN parameters, but does not add meaning beyond what the schema already provides. Thus a 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 clearly states the tool fetches stock rankings for northbound/Shanghai/Shenzhen Stock Connect holdings, with the specific focus on holding-change rankings over different periods. This verb+resource pairing is specific and distinguishes it from generic quote tools, though it does not explicitly contrast with sibling tools like get_northbound_realtime or get_northbound_history.

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 explains the tool can view rankings by different periods, but provides no guidance on when to choose this tool over siblings. It does not mention alternatives or exclusion criteria, leaving the agent to infer usage context from the tool name alone.

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

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

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds value by stating the tool returns both intraday inflow curves and a Stock Connect summary in one call, which is useful behavioral context beyond the annotations.

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 sentence concisely packs the tool's purpose, output, and use case with no redundancy or filler. Perfectly sized for one simple parameter.

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, no output schema, and one parameter, the description adequately explains what the tool returns and why it is used. It could mention update frequency or more detail about the data, but it is not necessary for basic 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?

Schema coverage is 100% with the 'direction' parameter fully described (north/south, default north). The description merely mentions '北向/南向' without adding new syntax or details, so the baseline of 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?

Description clearly states the tool fetches real-time northbound/southbound capital data, returning intraday inflow curves and Stock Connect summary. This distinguishes it from siblings like get_northbound_history and get_northbound_holding_rank.

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 phrase '用于判断当日外资动向' implies usage context (judging the day's foreign capital trends), but there is no explicit comparison to alternatives or exclusion criteria. Usage guidance is implied rather than stated.

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=true and openWorldHint=false, and the description adds return content details. However, it does not disclose additional behavioral aspects like data freshness, pagination, or access restrictions. It adds some context but not rich behavioral 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 a single, front-loaded sentence that states the purpose and output without unnecessary words. It is appropriately sized and compact.

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 only 2 parameters, high schema coverage, and readOnly annotations, the description is mostly complete. It mentions the return content, which is useful since there is no output schema. However, it lacks usage guidance or caveats, so a 4 is appropriate.

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 both parameters (symbol and date), so the schema fully documents them. The description does not add extra meaning beyond the schema, which is the baseline for high coverage.

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 option dragon-tiger list data and specifies the outputs (buy/sell volumes and position rankings per seat). It explicitly uses '期权' (options) to distinguish from the generic dragon-tiger siblings like get_dragon_tiger_list.

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 option-specific dragon-tiger data through the tool name and '期权' marker, but it does not explicitly state when to use this versus alternatives or provide exclusions. No when-to-use or when-not-to-use guidance is given.

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=true and openWorldHint=false, providing the safety profile. The description adds information about the return content (buy/sell large and small order proportions) but does not disclose other behavioral traits such as data source limitations, trading session dependencies, or interpretation nuances. This is a modest addition beyond the annotations, consistent with them.

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 that starts with the primary action ('获取盘口大单占比') and then provides the return details. There is no redundant or filler content; every word contributes to understanding the tool's function.

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 tool has a simple structure with one parameter, no output schema, and read-only annotations. The description is complete enough for the core function, stating both the subject (large order proportions) and the output categories (buy/sell, large/small). Since there is no output schema, the description covers the return semantics reasonably well. It could benefit from additional context like how the proportions are calculated or any limitations, but for the tool's simplicity, 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?

The input schema fully describes the single 'codes' parameter with a clear format and example: '股票代码数组，如 ["sz000858", "sh600519"]' (stock code array, e.g., ["sz000858", "sh600519"]). Schema description coverage is 100%, so the description does not need to compensate. The tool description itself does not add any additional parameter information, 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.