QuantSonar

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

With no annotations, the description discloses the 403 error for low-tier plans, the JSON array output structure, and field names. It does not discuss edge cases like inclusive dates or empty results, so it offers some behavioral context but not rich detail.

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

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

The description is compact and well-organized, starting with a short purpose line, then the access requirement, and a clear parameter list with return format. It is not verbose, though the Args block is duplicative of the schema.

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

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

Given the low complexity, the output schema, and the 100% parameter coverage, the description adequately covers the purpose, required plan, and return format. It leaves minor gaps like date inclusivity, but is sufficient for basic use.

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?

All four parameters have descriptions in the input schema (100% coverage), and the description largely repeats them. The mutual exclusivity of trade_date vs start/end is already captured in the schema, so the description adds no additional parameter semantics beyond the baseline.

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 identifies the tool as '复权因子（行情数据）' and documents the return fields, making it clear that it returns adjustment factors. However, it lacks an explicit action verb and does not mention the distinction from sibling tool etf_adj_factor, so it is clear but not fully differentiated.

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 notes the Starter plan requirement and the trade_date vs start/end exclusivity, but does not provide guidance on when to use this tool over related tools like etf_adj_factor or daily. The usage context is implied by the data returned.

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

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

No annotations are provided, so the description must disclose behavior. It discloses an error condition (403 on low-tier), the output format (JSON array with specific fields), and the data content. It does not state whether the operation is read-only (obvious) or discuss potential side effects, rate limits, or behavior with missing parameters. Some transparency is present but not comprehensive.

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

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

The description is efficiently structured with a clear purpose statement, a prerequisite note, then Args and Returns sections. The long list of return fields is necessary for clarity. No redundant or filler content is present.

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

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

Given three optional parameters, fully documented in the schema, and an output field list covering all return values, the description is fairly complete. It lacks a note about behavior when no parameters are provided (since all are optional), and it does not explain how the date range works, but these are minor gaps. The PRO requirement adds important 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 schema covers 100% of parameter descriptions, and the Args section in the description exactly repeats those descriptions without adding extra meaning (e.g., relationships between parameters, formatting examples, or default behavior). Baseline 3 is appropriate because the schema already documents the parameters sufficiently.

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

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

The description states the tool's purpose: '券商研报盈利预测（财务数据）' (broker research report earnings forecast financial data), which clearly indicates it provides analyst report forecast data. It does not use an explicit verb like 'retrieve' but the intent is unambiguous. It is distinct from siblings like 'forecast' or 'fundamentals' by focusing on broker research reports.

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 mentions a prerequisite (PRO package) and that low-tier calls return 403, which is useful. However, it does not explicitly state when to use this tool over alternatives or provide exclusion criteria. The usage context is only implied by the tool's name and subject matter.

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

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

With no annotations provided, the description carries the full burden. It discloses the subscription requirement and error behavior (403 for low-tier), and also specifies the return format as a JSON array with named fields. This is meaningful transparency for a data-fetching 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 compact and well-structured, front-loading the purpose and then listing parameters and return fields in a clear format. No filler words. It is slightly verbose with the args list but 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?

Given the tool's moderate complexity (5 optional params, output schema exists), the description covers the essential aspects: all parameters, return fields, and the PRO access requirement. It is complete enough for an agent to invoke the tool correctly.

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

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

The input schema already has 100% parameter coverage with descriptions. The description repeats the same parameter descriptions and examples (e.g., period format), adding little beyond what the schema already provides. 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 identifies the tool as providing financial audit opinions (财务审计意见) for financial data, which distinguishes it from sibling tools like balance_sheet or income. The resource is clear, though the verb is implicit (implied 'get' or 'retrieve') rather than explicit.

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 a key prerequisite: requires PRO or higher package, with low-tier calls returning 403. This helps set expected usage context but does not give explicit guidance on when to prefer this tool over alternatives or when not to use it.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that lower-tier plans receive 403 errors and specifies the return format (JSON array) and output fields. However, it does not mention other behaviors like error handling, required parameter combinations, or whether data is adjusted for splits. The plan requirement and field list provide some transparency but omit deeper behavioral context.

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 well-structured into sections: title, access requirement, Args, and Returns. It is appropriately sized for a tool with many parameters and output fields, with no fluff. Each line serves a purpose, making it easy to scan and understand.

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

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

The description covers access requirements, parameter formats, and output fields. Combined with the input schema (which provides parameter details) and the existence of an output schema, it gives a fairly complete picture of what the tool does and returns. It does not explicitly state use cases or parameter interdependencies, but for a data retrieval tool, it is largely 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 input schema already describes all 7 parameters with detailed descriptions (100% coverage). The description's Args section essentially repeats those descriptions with the same examples (e.g., period format). It adds no new semantic information beyond what the schema 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 identifies the tool as 'Balance Sheet (Financial Data)' and lists parameters and return fields that make it clear this tool retrieves balance sheet data. While it lacks an explicit verb like 'retrieve' or 'query', the structured parameter list and return fields leave no doubt about its function. It does not explicitly contrast with sibling tools like 'income' or 'cash_flow', but the name and content are sufficiently specific.

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 only mentions an access requirement: 'Requires Starter or above plan (lower tier calls return 403)'. It provides no guidance on when to use this tool versus related financial statement tools, nor any conditions or exclusions beyond the access level. The user must infer from the name that this is for balance sheet 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?

The description discloses the return format (JSON array) and the exact fields returned, which provides some transparency beyond the schema. However, it does not explicitly state that the tool is read-only, nor describe behavior when filters are omitted or when no matches are 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 compact and well-structured with clear 'Args' and 'Returns' sections. The only minor redundancy is the repeated 'ETF' in the title and parenthetical.

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

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

The description covers all parameters and return fields, which is useful for a query tool. However, it does not explain the default query behavior when all parameters are optional, nor how multiple filters interact, leaving some ambiguity for a user trying to construct a valid request.

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 describes all five parameters with identical descriptions. The description's Args section simply repeats the schema content, adding no new semantic information. Since coverage is 100%, a 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 identifies the tool as providing ETF basic information (ETF 基础信息) and lists filtering parameters, but lacks an explicit verb like 'query' or 'get', and does not distinguish it from sibling tools like 'stocks' or 'etf_daily'.

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 instead of alternatives such as etf_daily or tracking_indices. The description only lists parameters without any context about use cases 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?

Without annotations, the description carries the burden and discloses key behaviors: PRO plan mandatory (403 otherwise), return format as JSON array, specific fields, and the mutual exclusivity of trade_date with start/end. This goes beyond a simple 'get' declaration.

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, front-loaded with purpose and access requirements, followed by structured Args and Returns sections. No unnecessary prose.

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 data retrieval tool with an output schema present, the description covers access constraints, all parameters, and return fields. It is sufficient for the agent to invoke correctly, though it omits potential details like pagination or date-range behavior.

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

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

Schema description coverage is 100% and the description repeats the same parameter descriptions (e.g., '证券代码（带后缀）'), adding no new meaning beyond the schema. 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 identifies the resource as block trade market data (大宗交易行情数据). It distinguishes from siblings by naming a unique data category, though it lacks an explicit verb like 'get' or '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?

No guidance on when to use this tool vs alternatives. It mentions a PRO plan requirement and the trade_date mutual exclustivity constraint, but these are prerequisites, not usage 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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It discloses the plan requirement (403 error for low-tier) and the return format (JSON array with listed fields). However, it does not mention pagination, data range limits, or behavior when no parameters are provided. The disclosure is adequate but not rich.

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

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

The description is efficiently structured with an initial summary, a prerequisite note, a parameter list, and a return field list. It is concise and front-loaded with the key purpose. A minor inefficiency is that parameter descriptions duplicate the schema, but overall it is well-organized and every section 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?

The description includes the plan requirement, a full parameter list, and return fields. However, it lacks guidance on parameter combinations (e.g., whether symbol+period is required, how to filter by date) and does not clarify that all parameters are optional yet likely require at least one filter. With 8 parameters and no required fields, this 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 input schema provides descriptions for all 8 parameters (100% coverage). The description repeats these parameter descriptions without adding extra semantic meaning. Since schema coverage is high, a baseline of 3 is appropriate; the description adds no additional parameter insights 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 identifies the tool as '现金流量表（财务数据）' (cash flow statement financial data), which clearly indicates the resource being retrieved. While no explicit verb is used, the tool name 'cash_flow' and the description make it obvious this is a retrieval tool for cash flow statements, distinguishing it from siblings like balance_sheet and income.

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 states a prerequisite (Starter or above plan, low-tier returns 403) which is useful context. However, it provides no explicit guidance on when to use this tool versus alternatives, nor does it mention exclusions or typical use cases. Usage is implied by the tool name and resource type.

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

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

With no annotations, the description takes on full responsibility. It discloses the subscription requirement and the resulting 403 response, which is important behavioral context. It also outlines the return format as a JSON array with specific fields, adding clarity beyond the schema. It does not discuss limitations like pagination or rate limits, but for a read-only list tool, this is adequate.

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 well-structured with a one-line summary, a requirement line, and clearly labeled 'Args' and 'Returns' sections. It is reasonably concise for a tool with five parameters. However, the Args section repeats schema information, which is slightly redundant, but the overall organization is clear 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 tool's complexity (five optional parameters, no required fields), the description is fairly complete. It covers the subscription constraint, parameter usage (mutual exclusivity), and return fields. An output schema exists, so the description doesn't need to detail every field. Missing are concrete usage examples, but they are not essential for a straightforward data retrieval 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 coverage is 100%, so all parameter descriptions are present in the input schema. The Description's 'Args' section essentially duplicates the schema descriptions without adding new meaning, such as examples, relationships between parameters, or value constraints. Therefore, it meets the baseline but does not exceed it.

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 '概念/题材板块成分股（行情数据）' (concept/theme sector constituent stocks with market data), which identifies the specific resource and the type of operation. It distinguishes itself from sibling tools like 'concepts' (which likely lists concepts) by focusing on members. However, it does not explicitly contrast itself with similar tools, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage constraints: it notes that PRO or higher subscription is required (lower tiers get a 403) and explains that trade_date is mutually exclusive with start_date/end_date. However, it gives no guidance on when to choose this tool over alternatives, nor does it mention any exclusions or preconditions beyond the subscription level.

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

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

With no annotations provided, the description carries the full burden and does well: it discloses the PRO plan requirement, the 403 error for lower tiers, the mutually exclusive nature of trade_date with start/end dates, and the exact return format with field names. This goes beyond minimal behavioral disclosure, though it does not cover rate limits or data update frequency.

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 well-structured: a clear title, a permission note, an Args list, and a Returns list. It is front-loaded and every line serves a purpose. It repeats schema information, which adds some redundancy, but the organization makes it easy to scan.

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 data retrieval tool with 6 optional parameters and an output schema (return fields listed), the description covers purpose, parameters, permissions, and return format. It lacks explicit guidance on alternative tools and does not explain the meaning of fields like 'leading' or 'level', but overall it provides enough context for correct invocation.

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

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

Input schema has 100% description coverage for all 6 parameters, so the baseline is 3. The description duplicates the schema's parameter descriptions but adds no new meanings beyond what is already in the schema. The Returns section adds value for output understanding, but not for parameter semantics specifically.

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

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

The description clearly identifies the resource as '概念/题材板块指数（行情数据）' (concept/theme sector index market data), which distinguishes it from generic market data tools. However, it lacks an explicit verb like 'query' or 'retrieve', and does not directly compare to sibling tools like concept_members or industries, so it does not fully meet the 5-level standard.

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 a usage constraint (requires PRO plan, returns 403 otherwise) but gives no guidance on when to choose this tool over alternatives. There is no mention of when to use concepts vs. concept_members, index_daily, or industries, nor any exclusions or contextual recommendations.

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

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

With no annotations, the description carries the full burden. It does disclose the return shape (JSON array with listed OHLC fields) and the mutually exclusive date modes, adding useful behavior context. However, it omits whether symbol is required, how empty results are handled, pagination or limits, and doesn't explicitly state that this is a read-only market data operation.

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, well-structured, and front-loaded: a one-line summary, an Args list, and a Returns list. Every line earns its place, with no redundancy 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 straightforward OHLC endpoint, the description covers the parameter modes and return fields well. However, the input schema marks all parameters as optional while the description never clarifies that symbol is effectively required or what happens when no dates are supplied, leaving a meaningful gap for an agent building a valid request.

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 parameter names and formats are already documented. The description adds meaningful semantics by explaining the trade_date exclusivity with start/end dates and by giving a concrete symbol example with the suffix format, going beyond the schema's terse 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 opens with '日线行情（OHLC）' clearly identifying daily OHLC market data and lists the returned fields, making the resource unambiguous. However, it lacks an explicit verb like 'get' and does not explicitly differentiate itself from siblings such as etf_daily or index_daily, so it doesn't fully stand apart.

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 a useful in-parameter note that trade_date is mutually exclusive with start/end dates, which guides invocation. But there is no mention of when to use this tool versus its many siblings (etf_daily, index_daily, fx_daily), no alternative recommendations, and no exclusions or conditions for use.

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

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

With no annotations, the description discloses the plan requirement and error behavior for low-tier calls, and describes the return fields. However, it does not mention behavior when all parameters are omitted, sorting, or other potential side effects.

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 well-structured with a title, requirement note, args, and returns. It is relatively concise but repeats schema information, making it slightly redundant.

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?

An output schema exists and the description lists return fields, but it lacks details on parameter interactions, such as what happens if only symbol is provided or if no dates are specified. The optional nature of all parameters is unexplained.

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 description's Args section duplicates the schema descriptions exactly, adding no new meaning. The baseline of 3 applies as the schema already documents all parameters.

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 identifies the tool as a financial disclosure calendar and clearly states it returns a JSON array of disclosure dates. However, it lacks an explicit verb like 'get' or 'list', and does not differentiate from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance is the PRO requirement and 403 error for lower tiers. It implies usage for retrieving disclosure dates but offers no explicit comparison to alternatives or when-not-to-use conditions.

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

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

It discloses the entitlement requirement, the return format (JSON array with named fields), and the mutually exclusive date parameters. It does not explicitly state that this is a read-only operation, nor does it describe error behavior for invalid inputs or missing data. With no annotations present, the description carries the full transparency burden but only partially fulfills it.

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

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

The description is compact and well-structured with plan, args, and returns sections, making it easy to scan. The title phrase is repeated at the start, and the Args list duplicates the schema descriptions, adding minor redundancy, but it remains appropriately sized.

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 data-retrieval tool, the description covers the core purpose, plan restriction, and return fields. However, it does not specify that at least one date input is required or that symbol is mandatory, and with all parameters optional in the schema, an agent might call the tool with no arguments. Lacking example usage or edge-case behavior, it is 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 schema already provides descriptions for all four parameters (100% coverage), and the description's Args section repeats them verbatim without adding new meaning. The mention that trade_date is exclusive with start/end is already present in the schema. Thus the description adds no additional 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 clearly states the tool provides '筹码分布与胜率' (chip distribution and win rate) and lists the return fields, making the resource and scope understandable. However, it lacks a strong imperative verb like 'retrieve' and does not differentiate it from sibling tools such as 'daily' or 'technical_factors'.

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 notes the Expert+ plan requirement and warns of 403 responses for lower tiers, which is a valuable precondition. However, it does not explicitly state when to use this tool versus other market data tools, nor does it mention exclusions. The mutual exclusivity of trade_date vs. start/end is parameter guidance, not tool-selection guidance.

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

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

With no annotations provided, the description carries the full burden. It discloses the plan requirement and the return format (JSON array with fields), which is useful. However, it lacks details on data scope (e.g., whether symbol is required, date ranges), pagination, or rate limits. It gives some transparency but not comprehensive behavioral 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 well-structured: high-level purpose first, then plan requirement, then all arguments, then return fields. It is concise and easy to scan, though it redundantly restates parameter info already present in the schema. Still, the organization earns a 4.

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

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

The description covers purpose, plan requirements, all parameters, and return fields. Since an output schema exists, the return field list is adequate. However, it does not clarify parameter interactions (e.g., whether symbol alone is sufficient or if date ranges are required) and fails to differentiate from similar sibling tools like 'distribution'. This leaves some gaps for a complete picture.

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 all 6 parameters (100% coverage), so the baseline is 3. The description repeats the parameter names and descriptions in the Args section without adding additional semantic detail beyond what the schema already provides. Thus, no extra value is added.

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 as '分红送股' (dividend and stock bonus), indicating it retrieves dividend distribution data. It lists specific parameters like record_date and ex_date, which distinguish it from broader sibling tools such as 'distribution'. However, it does not explicitly contrast itself with siblings, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the plan requirement (Starter and above, lower tiers return 403), which gives some usage context. However, it provides no explicit guidance on when to use this tool versus alternatives like 'distribution' or 'fundamentals', nor does it state when not to use it. Usage is implied rather than explicitly directed.

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

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

With no annotations, the description carries the behavioral transparency burden. It discloses output fields and the trade_date exclusivity rule, which is useful. However, it does not explain what happens when symbol is omitted, whether date ranges are limited, or what the adj_factor values represent, leaving meaningful behavioral ambiguity.

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

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

The description is compact and front-loaded, with a clear Args/Returns structure and no filler prose. The opening 'ETF 复权因子（ETF）' is slightly redundant, but overall every line is purposeful and appropriately sized.

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?

An output schema exists, so the description does not need to fully explain return values, and it does cover parameter formats and the exclusivity constraint. However, with all parameters optional, it leaves open questions about required inputs, default date ranges, and query limits, which are important for a financial data endpoint.

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 description's Args section largely repeats the schema's parameter descriptions. It adds no new semantics beyond what the schema already states, so the baseline of 3 applies. The 'with start/end mutually exclusive' detail is already present in the schema too.

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 identifies the specific resource (ETF adjustment factor) and lists the output fields, making its purpose clear. It does not use an explicit verb like 'retrieve', but the Args/Returns structure implies a data-fetching tool. The mention of 'ETF/板块/外汇/港股等' helps distinguish it from general stock adjustment factor tools, though it does not explicitly name sibling 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 given for when to choose this tool over alternatives such as adj_factor or etf_daily. The only usage-related note is that trade_date is mutually exclusive with start_date/end_date, which is a parameter constraint, not tool-selection guidance. This leaves the agent to infer applicability from the name and sibling list.

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

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

With no annotations, the description carries the burden of explaining behavior. It discloses the return format (JSON array with specific fields), the mutual exclusivity of trade_date against start/end, and the exact-match behavior for symbol. It does not mention any side effects, permissions, or rate limits, but for a read-only data query, this is adequate. The description adds value by detailing the output fields.

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

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

The description is concise and well-structured, with a clear title, an Args section, and a Returns section. Every line is informative and there is no redundancy or fluff. It fits 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?

The description covers the essential aspects: what it does, the parameters, and the return structure. However, it lacks explicit guidance on when to use this tool vs similar daily-data tools, and it doesn't mention any pagination or limits. Given that an output schema is present (as indicated), the return field list is a helpful addition, but the absence of usage differentiation makes it slightly 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?

All four parameters already have descriptions in the schema, and the description largely repeats those descriptions verbatim. It adds no new semantic meaning beyond the schema, such as examples or edge cases. The only additional context is the explicit note that trade_date is mutually exclusive with start/end, which is already present in the schema's trade_date description. Therefore, the description adds minimal value over 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 'ETF 日线行情（ETF）' which identifies the tool as providing daily market data. It further specifies that the symbol can be ETF, sector, forex, HK stock, etc., giving a broad but clear scope. However, it does not explicitly distinguish itself from sibling tools like 'daily' or 'index_daily', so it's not fully differentiated.

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 a usage pattern with parameters, implying it is used for retrieving daily market data for a given symbol over a date range or single date. It does not explicitly state when to prefer this tool over alternatives such as 'daily' or 'fx_daily', nor does it list any exclusions. Therefore, 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?

With no annotations, the description carries the burden of behavioral disclosure. It does disclose the 403 response for insufficient plan level and lists return fields, but it does not clarify whether the operation is read-only (likely safe), how the date parameters interact with period, 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 well-structured with Args and Returns sections, and it is concise without unnecessary fluff. It includes the essential purpose and return fields, though it repeats some schema information, which is acceptable for clarity.

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

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

The description covers the tool's purpose, parameters, return schema, and a usage prerequisite, which is helpful. However, it lacks guidance on parameter combinations (e.g., whether start_date/end_date are required together), and the absence of annotations means more behavioral context would be beneficial for a data-retrieval 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 input schema already provides descriptions for all four parameters with 100% coverage, and the tool description repeats these same descriptions. It adds no extra meaning beyond the schema, such as default behaviors or parameter interdependencies, 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 indicates this tool provides 业绩快报 (financial performance express) data, listing specific return fields like revenue and net profit. It is distinct from sibling financial statement tools (balance_sheet, income) by focusing on express performance reports, though it lacks an explicit verb like 'retrieve'.

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 states a prerequisite: requires Starter or higher plan, and warns that lower tiers return 403. However, it does not provide any guidance on when to use this tool versus siblings like fundamentals or income, nor does it mention alternative tools for similar 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?

With no annotations provided, the description carries the full burden. It discloses the access tier requirement and the 403 behavior for low-tier callers, and specifies the return type (JSON array) and fields. However, it does not describe other behavioral aspects such as data freshness, required parameter combinations, or the meaning of return fields, which is a moderate gap.

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 well-structured with clear sections for Args and Returns. It front-loads the resource name and includes the essential access requirement, then lists parameters and return fields. It is reasonably concise and every section earns its place, though the return field list is somewhat exhaustive.

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 optional parameters) and the presence of an output schema, the description covers the essential context: the access constraint, parameter formats, and return fields. It does not explain the semantics of each return field, but the output schema can fill that gap. The description is adequate for an agent to invoke the tool correctly.

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

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

Schema description coverage is 100%, and the Args section in the description repeats the same parameter descriptions without adding additional meaning. The examples (e.g., 000001.SZ, 20251231) are also present in the schema, so no extra semantic value is provided by the description.

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 identifies the resource as '业绩预告（财务数据）' (earnings forecast/financial data), which is a specific resource type. It does not explicitly state an action verb like 'get' or 'list', but the Args and Returns sections clearly indicate it retrieves forecast data. It distinguishes from siblings like 'express' by the term '业绩预告', though it does not explicitly contrast 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 description provides a prerequisite (Starter or higher package, with 403 otherwise) but gives no guidance on when to choose this tool over siblings or when not to use it. There is no mention of alternatives or exclusions. The usage context is only implied by the resource 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?

With no annotations, the description carries the transparency burden. It discloses the plan requirement and the 403 error for lower tiers, and it lists the return fields. It does not mention rate limits, reads, default rows, or error behavior for missing/invalid parameters, and leaves symbol's requirement ambiguous.

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

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

The description is compact and well-structured, with a short intro followed by clean Args and Returns blocks. Every line provides useful information, and there is no unnecessary prose.

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 straightforward data retrieval endpoint, and the description covers plan requirements, parameters, and return fields. However, it does not state that symbol is effectively required even though the schema allows null, and it does not specify behavior when no dates are provided—leaving moderate ambiguity for the agent.

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

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

Schema coverage is 100%, and the description's Args section essentially mirrors the schema's descriptions. It adds no new meaning beyond what is already in the input schema, so the baseline score of 3 applies.

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

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

The description clearly identifies the tool as providing daily fundamental metrics (PE/PB/turnover/market cap) and classifies it as market data. The resource and scope are specific enough to distinguish it from price-data siblings like 'daily' or 'realtime', though it does not explicitly name those 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?

The description gives a prerequisite (Starter plan required, 403 on lower tiers) and notes that trade_date is mutually exclusive with start/end dates. However, it does not explicitly state when to use this tool over other fundamental or market-data siblings; usage context is only implied by the title and field list.

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

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

With no annotations, the description provides useful behavior beyond the schema: it notes '代码原样匹配' (exact symbol matching), the default symbol, and the mutual exclusivity of trade_date with start/end dates. It also lists the exact return fields. This is sufficient for a simple data retrieval tool, though it doesn't cover pagination, rate limits, or data availability.

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 tightly structured with separate Args and Returns sections, each line serving a purpose. It avoids fluff and front-loads the core purpose. Length is appropriate for the tool's complexity.

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 low-complexity data retrieval tool, the description covers all essential invocation details: what data is returned, the default symbol, and how to specify dates. The output schema exists, so listing fields is redundant but helpful. The only gap is the lack of sibling differentiation, but that's not required for correct usage.

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

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

Schema description coverage is 100%, so the baseline is 3. The description repeats the parameter meanings and default values without adding new semantics. It does organize them cleanly, but no additional nuance 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 opens with '外汇日线（默认 USDCNH）' (Forex daily line, default USDCNH), clearly identifying the tool as providing forex daily OHLC data. This is specific and distinguishes it from sibling daily tools like 'daily' or 'etf_daily', which cover stocks and ETFs respectively.

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 forex data via the asset class in the title and default symbol, but it does not explicitly state when to use fx_daily versus alternatives like daily or etf_daily. It also doesn't mention any exclusion criteria or scenarios where another tool would be preferred.

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

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

With no annotations, the description carries the burden and does disclose that lower-tier plans return 403, which is a meaningful failure mode. It also lists the return fields, giving the agent expectations about the output. It doesn't mention rate limits or pagination, but the plan requirement is substantial context.

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

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

The description is compact and well-structured: a one-line purpose, plan constraint, Args list, and Returns list. It front-loads the purpose and every section serves a distinct 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?

For a moderate query tool with 5 optional parameters, the description covers the plan requirement, parameter formats, and return schema. It lacks explicit defaults for omitted parameters, but the overall information is sufficient for an agent to invoke the tool correctly.

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

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

The input schema already describes all 5 parameters with 100% coverage, so the description's parameter section adds little beyond repeating the schema. It does provide an example symbol format and enumerates the allowed values for trade_type and holder_type, which matches the schema's 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 identifies the tool as querying "重要股东增减持（行情数据）" (major shareholder increase/decrease holdings market data), which is a specific resource and distinguishes it from siblings like shareholders or block_trade. The verb is implied (query/list), but the resource is unmistakable.

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 notes the PRO+ plan requirement and 403 error for lower tiers, giving a concrete precondition. However, it doesn't explicitly state when to choose this over sibling tools like shareholders or top_list, nor does it 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 no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the plan requirement and 403 behavior, which is valuable. However, it does not elaborate on other behavioral aspects such as data coverage, date filtering logic, or potential response limits, leaving some uncertainty.

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 well-structured with a title, access note, parameter list, and return fields. It is somewhat lengthy and duplicates the schema, but the organization makes it easy to scan. The access note is extra value, and the list of return fields could be considered redundant given the output schema, but overall it is acceptably 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 has 8 optional parameters and a rich output schema. The description covers the access requirement and lists all fields, but it lacks usage context, such as how to choose between period and start_date/end_date, or the meaning of report_type options beyond the ellipsis. This incomplete guidance for a complex financial data tool keeps it at a moderate score.

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 parameter descriptions in the description exactly replicate those in the input schema, which already has 100% coverage. No additional meaning is added beyond the schema. The 'Returns' section lists output fields but does not clarify parameter interactions or usage nuances, 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 begins with '利润表（财务数据）' which clearly identifies the tool as providing income statement financial data. This distinguishes it from sibling tools like balance_sheet and cash_flow. While there is no explicit verb, the 'Returns' section confirms its data-retrieval purpose, making the intent 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 alternatives. It only mentions a prerequisite (Starter and above plan) and the 403 error for lower tiers, but does not explain scenarios or reference any other tools. This leaves the decision to the agent without contextual direction.

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

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

With no annotations, the description carries the burden of disclosing behavior. It discloses the return format and field list, which is useful. However, it does not mention potential pitfalls like date range coverage, data update frequency, or error behavior. It provides basic transparency but lacks richer context.

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

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

The description is extremely concise, with the main purpose front-loaded and parameters/returns presented in a clear, structured list. Every line adds necessary information 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 simple data-retrieval tool, the description covers the essential aspects: purpose, parameters, and return fields. It lacks clarity on default date range when no dates are supplied and on data update behavior, but these are minor gaps given the tool's simplicity and the presence of 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?

Schema coverage is 100%, so the baseline is 3. The description adds value by explicitly noting that 'trade_date' and 'start_date'/'end_date' are mutually exclusive ('二选一'), which is not enforced in the schema. It also restates parameter formats clearly.

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

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

The description clearly identifies the tool as returning daily index data, specifically for the Shanghai Composite Index by default. It distinguishes from sibling tools like 'daily' (stock data) and 'etf_daily' by specifying '指数' (index) and the default symbol. The 'Returns' section confirms the data resource.

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 'daily' or 'etf_daily'. The description only states parameters and returns but does not mention exclusions or compare with siblings. The usage context is only implied by the tool name and 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?

无注解信息，描述承担了行为透明度的主要责任。它披露了低档位调用返回403的访问限制、trade_date与start/end的互斥关系，以及返回的JSON数组字段。但未提及参数缺失时的行为（如symbol是否必须）、分页方式或速率限制，仍有透明度缺口。

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?

描述结构清晰，先点明用途，再列出参数和返回值，内容紧凑无冗余。每条信息（套餐限制、参数约束、返回格式）都有价值，且采用列表形式和分段，便于快速浏览。

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?

对于提供4个可选参数的数据查询工具，描述覆盖了目的、参数、返回字段和访问限制，已较为完整。但缺少参数是否必填、无数据时返回值形式等细节，且未提供输出结构定义（虽然描述列了字段）。整体虽不完美，但在无注解和输出结构缺失的情况下已算充分。

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?

输入模式已覆盖100%参数描述，但描述额外补充了trade_date与start_date/end_date的互斥关系，并给出了symbol的示例（000300.SH），这些信息超出架构描述，为参数使用提供了额外语义。

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?

描述以名词短语'指数成分与权重（指数）'清晰指出工具返回的是指数成分股及权重，资源类型明确。虽未使用显式动词（如'获取'），但结合Args和Returns已足够明确用途，且与兄弟工具（如index_daily、concept_members）在数据内容上区分明显。

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?

描述提供了使用前提（需要Starter及以上套餐，低档位返回403）以及参数之间的互斥约束（trade_date与start/end二选一），但未说明何时应使用该工具而非兄弟工具（如index_daily或concept_members），缺少替代场景指引。

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

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

With no annotations provided, the description carries the full burden. It discloses the plan entitlement (403 on lower tiers) and the return format (JSON array with a field list). However, it does not mention rate limits, pagination, behavior for missing parameters, or whether certain parameters are mutually exclusive. The disclosure is moderate 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 front-loaded with a concise title and requirement note, followed by a structured Args list and a Returns field list. It is reasonably concise, though the Args section repeats schema content, creating some redundancy. Overall, it is well-organized 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?

The description includes the return field list and a plan prerequisite, which is helpful. However, with no required parameters and no explanation of parameter relationships (e.g., period vs. end_date), an agent might not know what to pass. The absence of usage guidance and sibling differentiation further limits completeness, making it adequate but not thorough.

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

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

Schema description coverage is 100%, so the schema fully documents each parameter. The Args section in the description exactly duplicates the schema descriptions (e.g., 'symbol: 证券代码（带后缀）'), adding no new meaning. Thus, the description provides no extra semantic value beyond the schema, warranting the baseline score 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 '财务指标（财务数据）' clarifies that the tool provides financial indicators, and the subsequent Args and Returns sections make it clear it retrieves metrics like EPS, ROE, and margins. It lacks an explicit verb but is understandable. It does not explicitly differentiate from sibling tools like income or balance_sheet, but the reported fields indicate derived indicators rather than raw statements.

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 on when to use this tool versus alternatives. The only usage-related note is the plan requirement ('需要 Starter 及以上套餐（低档位调用返回 403）'), which is a prerequisite rather than a contextual recommendation. There is no mention of alternatives 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?

With no annotations, the description carries the full burden for behavioral disclosure. It does state the return format (JSON array with specific fields), which is helpful. However, it does not clarify behavior when 'symbol' is null (the parameter is optional with default null), nor does it mention whether this is a read-only operation, error conditions, or authentication needs. The description is mostly a structural schema, lacking richer behavioral context.

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 exceptionally concise and well-structured, with a clear title, Args section, and Returns section. Every sentence earns its place, and there is no fluff or redundant information. It is front-loaded with the tool's purpose and provides the essential parameter and return field list in a compact format.

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 (one optional parameter, no required fields), and the description covers the parameter and return fields adequately. However, the lack of an output schema in the structured data (though the description lists fields itself) and the missing behavior for null symbol leaves a completeness gap. The description is sufficient for a basic retrieval tool but not fully complete for an agent to predict all behaviors.

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

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

Schema description coverage is 100%, so the schema alone fully documents the 'symbol' parameter. The description does not add any meaning beyond the schema; it repeats the same example (000001.SZ). The parameter's optionality and the default-null behavior are present in the schema but their semantic implication (what happens when null) is undocumented. Baseline of 3 applies because 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 clearly identifies the tool as returning Shenwan industry classification (申万行业分类) for a stock symbol, with the resource being industry classification data. It distinguishes itself from sibling tools like 'concepts' or 'concept_members' by the specific domain (industry vs concept). The lack of an explicit verb like 'get' or 'retrieve' is minor because the Args/Returns structure implies a data retrieval operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. With many sibling tools (stocks, concepts, basic), the absence of usage context is a clear gap. No mention of what to do when 'symbol' is omitted or how this relates to other classification 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?

With no annotations, the description carries full burden. It discloses that PRO or above is required and that lower tiers return HTTP 403, which is useful operational context. It also mentions the return format. However, it does not disclose other behaviors like whether results are paginated, rate limits, or what happens if no required parameters are provided (since all are optional).

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

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

The description is concise and well-structured with labeled Args and Returns sections. Each line serves a purpose: explaining the tool type, subscription requirement, parameter meanings, mutual exclusivity, and return fields. There is no filler or redundant repetition beyond what's needed.

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

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

The description covers the core purpose, auth requirements, parameters, and return format, which is reasonably complete for a data-list tool. However, it does not explain what happens when no parameters are provided (all are optional), nor does it mention pagination or other typical listing behaviors. Given the absence of annotations, this leaves some 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 coverage is 100%, so each parameter has a description in the schema. The description adds extra value by explicitly noting that trade_date is mutually exclusive with start_date/end_date, which is not indicated in the schema. It also clarifies the limit_type values (U/D/Z). This goes beyond the baseline.

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 provides a limit-up/down list (涨跌停榜单) and identifies it as market data (行情数据). This is a specific resource, and the name 'limit_list' reinforces the purpose. It distinguishes from siblings like 'daily' or 'top_list' by its focus on limit-up/down events, though it doesn't explicitly call out 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 on when to use this tool versus sibling tools such as 'daily', 'realtime', or 'top_list'. The only usage-related info is the PRO subscription requirement and the note that trade_date is mutually exclusive with start/end dates, which is parameter behavior rather than tool selection guidance.

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

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

With no annotations, the description carries the full burden. It does disclose the 403 error for insufficient subscription tiers and the exact return format (JSON array with fields). However, it does not mention read-only status explicitly (though implied), rate limits, or error handling for invalid inputs.

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 well-structured with distinct sections for requirement, arguments, and returns. It is relatively concise, though the Args section duplicates the schema descriptions, which is mildly redundant. The main purpose is front-loaded.

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?

An output schema exists, so return-value details are not required. The description does not explain how the date parameters and period interact (e.g., whether period is an alternative to start/end_date). All parameters are optional, and no guidance on valid combinations is provided, leaving some ambiguity for agents.

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 full descriptions for all four parameters (100% coverage). The description's Args section repeats these descriptions verbatim, adding no new semantics such as valid combinations or parameter relationships. Baseline 3 is appropriate since 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 opens with '主营业务构成（财务数据）', which clearly identifies the resource as main business composition. Although it lacks an explicit verb like 'Get' or 'Retrieve', the Args and Returns sections make its data-retrieval purpose obvious, and it is distinct from sibling financial 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 mentions the premium requirement ('需要 PRO 及以上套餐（低档位调用返回 403）'), which is a prerequisite, but it does not provide guidance on when to use this tool versus alternatives like income or balance_sheet. No exclusions or preferred scenarios 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?

With no annotations provided, the description shoulders the transparency burden. It discloses the 403 error behavior for low-tier users and specifies the return format (JSON array with listed fields). It does not state explicitly that it is read-only, but '行情数据' implies a data retrieval operation.

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

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

The description is compact and front-loaded: purpose, access requirement, parameters, and returns are all covered in a concise block. No redundant text 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 data query tool, the description provides the essential context: what it does, access restriction, parameters, and output fields. The output schema exists, so return fields are redundant but harmless. It lacks only minor details like pagination or field definitions, but those are covered by the 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 description coverage is 100%, so baseline is 3. The description's parameter list merely repeats the schema's descriptions (symbol example, date format, and the trade_date mutual exclusivity). It adds no new meaning 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 provides '融资融券明细' (margin trading details) as market data. The verb '明细' and resource are specific and distinct from sibling tools, though it does not explicitly call out 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?

It mentions the PRO/PRO+ subscription requirement and that lower tiers return 403, which is a prerequisite/context. However, it does not explicitly state when to use this tool versus alternative data endpoints or provide exclusionary 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?

No annotations are provided, so the description carries the full burden. It discloses the PRO requirement, the specific 403 error on low-tier access, and the return format. This is strong for a read-only data retrieval tool, though it doesn't cover rate limits or data coverage nuances.

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 well-structured with Args and Returns sections, and front-loads the purpose. It is longer than minimal due to the detailed return field list, but every part serves a purpose. No wasted 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?

Given the tool's moderate complexity, the description covers the resource, permissions, error behavior, parameters, and output fields. The output schema exists, so the manual return list is extra but helpful. Minor gaps like maximum date range or pagination are acceptable here.

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%, but the description adds crucial semantics: it re-emphasizes the symbol pattern with an example and explicitly states the mutual exclusion between trade_date and start_date/end_date, which the schema does not convey. This goes well beyond the baseline.

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 '个股资金流向' (individual stock money flow), which identifies the resource and distinguishes it from sibling tools like moneyflow_hsgt. However, it lacks an explicit verb like 'get' or 'query', relying on the tool name to imply the action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides important context: PRO subscription required and low-tier returns 403, plus the mutually exclusive trade_date vs date range parameters. But it does not explicitly state when to use this tool over alternatives (e.g., moneyflow_hsgt) or provide 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?

With no annotations, the description carries the full burden. It discloses the return format (JSON array with specific fields), the error condition for insufficient plan level, and parameter constraints. This provides substantial transparency for a read-only data retrieval tool, though it could mention rate limits 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 well-structured with required plan, args, and returns, but the Args block duplicates the schema's property descriptions, making it redundant. A more concise version could integrate parameter details more efficiently.

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

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

The description covers the key context: the whole-market scope, the PRO requirement, the date parameter modes, and a clear return schema with field names. For a tool of this complexity, it is sufficient, though it does not explain the meaning of each returned field (e.g., ggt_ss vs hgt_ss) which might be helpful.

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 Args section in the description largely repeats the schema's descriptions. The only added value is the explicit '与 start/end 二选一' mutual exclusion, which is already present in the schema. No meaningful new semantics beyond the structured data.

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 '沪深港通资金流向（全市场）' (whole-market Stock Connect capital flow), providing a specific resource and action. It distinguishes itself from sibling tools like 'moneyflow' by emphasizing '全市场' (whole 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?

Mentions PRO+ requirement and the 403 error for lower tiers, which is useful context. Also notes the mutual exclusion of trade_date with start/end. However, it does not explicitly discuss when to use this tool versus sibling tools like moneyflow, northbound_holdings, or southbound_holdings, leaving comparison to 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?

No annotations are provided, so the description carries the burden. It discloses the return format and field list, and mentions the 403 error condition for insufficient plan level. It does not describe pagination, data limits, or behavior when no filter parameters are given, leaving some ambiguity.

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

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

The description is structured with a purpose line, a prerequisite line, Args, and Returns, which is easy to scan. However, the Args section repeats schema descriptions, making it slightly redundant without adding new 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?

The description covers purpose, plan requirements, parameter formats, and return fields. However, it does not explain required filter combinations or default behavior when all params are optional, which is a gap for a data query tool. Given the output schema exists, return values are covered, but usage constraints are missing.

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

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

Schema description coverage is 100% with descriptions like '代码原样匹配（ETF/板块/外汇/港股等）' and date formats. The Args section in the description duplicates this information exactly, adding no new semantic meaning. Baseline 3 applies because the schema already documents parameters well.

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

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

The description opens with 'ETF 净值（ETF）', clearly identifying the resource as ETF net value, and the Returns section confirms it retrieves a JSON array of NAV fields. However, it does not explicitly contrast with sibling tools like etf_daily or etf_adj_factor, so it's clear but not fully differentiated.

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 notes the requirement of Starter or higher plan with 403 for lower tiers, providing a prerequisite. It implies use for fetching NAV data but does not give any guidance on when to choose this over alternatives or what typical query scenarios look like.

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

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

With no annotations provided, the description carries full burden. It discloses important behaviors: the 60-second delay, sorting by publish time descending, the 403 error for lower-tier plans, and the return field structure. This adds substantive context beyond the schema.

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

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

The description is well-structured with clear Args/Returns sections and no wasteful prose. There is slight redundancy in the title line '（实时）（实时与快讯）', but overall it is concise and front-loaded.

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

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

The description covers access requirements, parameter details, and return format, which is sufficient for an agent to call the tool correctly. Optionality of date parameters is handled by the schema, and the output fields are explicitly listed.

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 baseline is 3. The description repeats the same parameter explanations (source, date format, importance threshold) without adding deeper depth or usage nuances 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 identifies the tool as real-time financial news ('实时财经快讯') from three named sources (cls/jin10/sina), with specific ordering and delay. This distinguishes it from sibling tools by specifying exact resources 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?

Provides clear context: real-time, 60-second delay, and Starter plan requirement. However, it does not explicitly mention when not to use this tool or compare it with alternative siblings like 'express' or 'realtime'.

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

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

With no annotations, the description carries the full burden. It discloses the low-frequency data cadence, retention of historical daily data, and the PRO plan requirement (lower tiers return 403). This adds significant behavioral context beyond the schema. It does not cover error handling beyond 403, but the disclosed traits are substantial.

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

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

The description is compact and well-structured with 'Args' and 'Returns' sections. Every sentence is essential, covering cadence, access requirements, and return fields. No fluff or redundancy. The front-loaded title phrase immediately conveys the resource.

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

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

Given the tool's complexity, the description covers data frequency, auth constraints, parameters, and return fields. It does not explicitly state default behavior when no dates are passed, but the query suggestion implies that is acceptable. The presence of an output schema further reduces the need to explain return values. Overall, fairly complete.

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

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

Schema coverage is 100%, so the baseline is 3. The description repeats parameter names and adds no new meaning beyond the schema. The note that trade_date is exclusive with start/end is already present in the schema description. No extra semantics provided.

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

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

The description opens with '北向持股明细（资金流向）' which clearly identifies the resource as northbound holdings details, distinguishing it from the sibling 'southbound_holdings'. Though it lacks an explicit verb like 'get' or 'query', the 'Returns' section confirms it provides data. 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 provides clear context on when to use this tool, explaining the disclosure rhythm change (no longer daily since Aug 2024) and giving a query suggestion: '查询建议不带日期或用较宽日期范围'. It does not explicitly name alternatives, but the context makes the use case clear. Lacks explicit 'when not to use' exclusions.

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

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

No annotations are present, so the description must convey behavioral traits. It does mention the PRO requirement and indicates that symbols are matched exactly ('代码原样匹配'). It also specifies date formats and returns a JSON array with listed fields. However, it does not disclose whether at least one parameter is required, how parameters interact, or any pagination/rate limits, leaving gaps in the behavioral picture.

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

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

The description is compact and well-structured, with a clear title, a brief note on subscription requirements, and separate Args and Returns sections. It avoids unnecessary detail and is easy to scan. The Args section repeats schema descriptions but does so succinctly, so the structure earns high marks.

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 an output schema and 5 optional parameters. The description covers parameter formats and return fields, but does not explain whether a symbol is effectively required, how date ranges are interpreted, or what the numeric fields (mkv, amount, etc.) represent. It also offers no comparison with sibling tools, so the context is adequate but not complete for a fully informed choice.

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% description coverage; every parameter includes a Chinese description that exactly mirrors the Args section in the tool description. The description adds no extra meaning beyond repeating the schema information, so the theoretical baseline of 3 applies. It includes one example (000001.SZ) which slightly aids understanding, but overall no new semantic value is added.

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 'ETF 持仓明细' (ETF holdings details), specifying the resource and the type of data returned. The purpose is unambiguous and the parameter list supports it. However, it does not explicitly distinguish from sibling tools like tracking_indices or etf_daily, so it is not a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance provided is the PRO subscription requirement and the 403 error for lower tiers. There is no information on when to prefer this tool over sibling alternatives, no exclusions, and no context on typical use cases. The agent is left to infer when 'portfolio' is appropriate.

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

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: refresh during trading, previous close after hours, batch limit of 200 symbols, and 403 error for low-tier plans. It also specifies return fields. This is strong behavioral transparency for a read-only quote tool, though it doesn't cover rate limits or error cases beyond 403.

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

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

The description is concise and well-structured, with a clear title, a brief behavior explanation, and a bulleted Args/Returns section. Every sentence adds value, and it is appropriately front-loaded with the core 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?

Given the low complexity (one optional parameter) and presence of an output schema, the description is quite complete. It covers batch limits, trading/non-trading behavior, access tier, and return fields. Minor omissions like rate limits and detailed error codes are not critical for this tool type.

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 description's Args section repeats exactly what the input schema already documents (symbol, comma-separated batch, up to 200, full market if omitted). No additional meaning is added beyond the schema, so baseline 3 applies.

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

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

The description clearly states it provides real-time quotes/snapshots for each security, with specific details about trading hours and fallback to previous close. This distinguishes it from sibling tools like 'daily' or 'basic' by emphasizing real-time versus historical 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 gives clear context about when data is current (trading period) versus stale (non-trading period), and mentions access requirements (Starter plan or higher). However, it does not explicitly name alternative tools or state when NOT to use this tool, leaving usage guidance implied rather than explicit.

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

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It discloses the PRO requirement and 403 error behavior, and notes the JSON array return format. However, it omits other behavioral aspects such as rate limits, pagination, data freshness, or what happens when no data matches the query.

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 well-structured with a title line, access requirement, argument list, and return description. It is slightly repetitive of the schema, but the information is front-loaded and easy to scan, making it efficient 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?

For a 5-parameter data retrieval tool with optional parameters and an output description, the description adequately covers purpose, access requirements, parameter formats, and return fields. It does not elaborate on edge cases or the interplay between dates, but overall it provides enough context for a typical query scenario.

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 restates each parameter with the same descriptions as the schema, adding no additional semantic meaning beyond what the schema already provides. It clarifies the distinction between end_date and enddate, but that is also present in 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 identifies the tool as returning 股东户数 (shareholder count) market data, with a specific resource and context. It mentions the data type and return fields, but does not explicitly distinguish it from sibling tools such as holder_trade or share_size, though the '行情数据' qualifier helps set it apart.

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 includes a usage constraint by noting the PRO subscription requirement and the 403 error for lower tiers, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. The intended usage is implied by the tool's purpose, but no direct 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?

With no annotations, the description carries the transparency burden and does well by disclosing the authentication requirement (403 for lower tiers), parameter constraints, and return fields. It omits rate limits and pagination, but for a read-only financial data endpoint this is a thorough 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 well-structured with separate Args and Returns sections, front-loaded with the purpose. Every sentence adds useful information with no redundancy 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 description covers all parameters, the auth requirement, the output format, and the exclusivity constraint. With an existing output schema and no required parameters, this provides a complete picture for an API of this 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 already has 100% coverage for all 5 parameters, and the description's Args section simply repeats the schema descriptions without adding new semantic value. Baseline of 3 is appropriate since 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 clearly states the tool returns ETF share and scale data, with specific output fields listed. However, it lacks an explicit verb like 'get' or 'query', making the purpose slightly less direct than ideal, even though the resource is well-defined and distinct from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage context by mentioning the required Starter or above plan and the mutual exclusivity of trade_date with start/end. It does not explicitly compare to alternative tools or state when to prefer this over siblings, so guidance is implied rather than explicit.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses the T+1 delay, the PRO-tier requirement with 403 behavior, and the return format (JSON array with specific fields). This is substantial but could mention pagination or error handling for missing data.

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

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

The description is concise and well-structured: purpose, constraints, args, and returns. It front-loads the core purpose in the first line and uses a clean format. Every sentence earns its place.

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

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

The description covers core context: T+1 lag, subscription requirement, mutual exclusivity of date parameters, and return fields. It also benefits from the presence of an output schema. It could be more explicit about what happens when neither trade_date nor start/end is provided, but overall it is complete for a data retrieval 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%, so the baseline is 3. The description repeats schema descriptions for symbol, start_date, end_date, and trade_date, and explicitly notes the trade_date vs. start/end mutual exclusivity, but does not add meaningful 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 identifies the resource as southbound (Stock Connect) shareholding details with fund flow, which distinguishes it from northbound_holdings. However, it lacks an explicit verb like 'get' or 'list', relying on the noun phrase '持股明细' to imply retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides important operational context (T+1 data lag, PRO subscription requirement, 403 for lower tiers) but does not explicitly state when to use this tool versus alternatives such as northbound_holdings or moneyflow_hsgt. Usage is implied rather than spelled out.

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

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

No annotations are provided, so the description must disclose behavioral traits. It discloses that the return is a JSON array with specific fields, which is useful. However, it does not mention whether filters are combined (AND), if at least one filter is required, if results are paginated or limited, or that it is a read-only operation. The behavioral info beyond the schema is minimal.

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 well-structured and concise: a short title, an Args list matching the schema, and a Returns section. It is front-loaded, easy to scan, and contains no unnecessary prose. The redundancy with the schema is acceptable and does not inflate length unnecessarily.

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 output schema covers return values, but the description lacks important contextual details for an AI agent. It does not state that all parameters are optional, how filters interact, or whether calling with no filters returns the entire universe of stocks (which could be a huge response). It also does not explain the distinction from sibling tools, leaving the agent without enough context to choose this tool confidently.

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 parameters with descriptions, so the schema already documents parameter meaning. The description repeats the same parameter descriptions without adding extra semantics such as filter combination logic, default behavior, or value formatting beyond what is in the schema. 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 identifies the tool as a stock list providing basic information, with a specific title '股票列表（基础信息）' and a Returns section defining the output fields. It is distinct from sibling tools like daily or fundamentals, although it does not explicitly name alternatives or state the scope (e.g., 'List all stocks matching filters').

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 lists filter parameters but does not state whether this should be used for querying basic stock metadata, whether it is the default for lookup, or what scenarios are better suited for other sibling tools. There is no explicit when-to-use or when-not-to-use guidance.

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

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

With no annotations, the description carries the burden. It discloses the 403 error for lower tiers and enumerates all output fields, which is helpful. However, it omits behavioral aspects like pagination, date range limits, data source, or empty-result behavior. Transparency is partial.

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 clearly segmented into Args and Returns. The PRO requirement is front-loaded, and every sentence carries useful information. It is compact without being under-specified.

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?

An output schema exists, so the return field list is a bonus. However, the description does not clarify whether a symbol is mandatory or how many of the date parameters are truly needed. It also fails to relate this tool to its sibling technical_factors_pro. These gaps make it incomplete 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 input schema already describes all four parameters with 100% coverage. The Args section repeats the same descriptions without adding new semantics. The only extra note—trade_date exclusivity—is also present in the schema. Therefore, the description adds little 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 opens with '技术面因子（行情数据）' which is more a category label than a clear function statement. It lacks an explicit verb like 'retrieve' or 'get', and does not distinguish itself from the sibling tool technical_factors_pro. However, the Returns section clarifies that it provides technical indicators for a security.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides concrete usage constraints: the PRO plan requirement and the exclusivity between trade_date and start/end dates. Yet it gives no guidance on when to prefer this tool over technical_factors_pro, daily, or indicators, and does not clarify whether a symbol is required. Usage context is only partially addressed.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses the permission requirement (403 on lower tiers), the return format (JSON array), the full list of fields, and the mutual exclusivity between trade_date and start/end. It does not mention pagination, rate limits, or behavior with no parameters, but for a data retrieval tool, it covers the key operational facts.

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 structured with clear sections: a one-line purpose, a permission note, Args, and Returns. It is front-loaded and free of fluff. The extremely long field list is necessary for a data tool with many indicators, but it does make the description lengthy. Overall, it is appropriately organized and not redundant.

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 data retrieval tool with hundreds of fields, the description provides the essential context: permissions, parameter formats, mutual exclusivity, and the full output field list. The output schema is present in the description itself. It lacks details like data frequency (implied daily by trade_date), error handling for invalid symbols, or date range limits, but these are not critical gaps given the richness of the rest of the description.

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 all four parameters already described in the input schema. The description's Args section repeats the same descriptions without adding new semantic information, except perhaps reinforcing the trade_date vs start/end exclusivity. Given the schema fully documents the parameters, the description adds marginal value beyond it.

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

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

The description clearly identifies the tool as a provider of technical factors (pro version) including adjusted prices and technical indicators, and labels it as market data. This distinguishes it from the sibling 'technical_factors' tool. However, it lacks an explicit action verb (e.g., 'get', 'retrieve'), relying on the noun phrase '技术面因子' to imply data retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states the prerequisite that Expert or higher tier is required and that lower tiers get a 403 error, which gives usage context. It also notes that trade_date is mutually exclusive with start/end dates. However, it does not explicitly compare this tool to siblings like 'technical_factors' or 'daily' or state when to prefer this over those alternatives. Usage is implied rather than directly guided.

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

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

With no annotations provided, the description appropriately discloses that lower-tier subscriptions result in HTTP 403, and it describes the return format. It does not cover rate limits or other edge behaviors, but for a read-only market data endpoint this is reasonable.

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

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

The description is compact and well-organized: a title line, a package requirement, an Args block, and a Returns block. Every sentence contributes useful information with no 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 four-parameter data retrieval tool with no annotations and an output schema, the description provides all necessary context: data source, access restrictions, parameter formats, and return fields. It is fully self-contained.

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

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

Schema coverage is 100%, so the description's parameter section largely repeats schema info, but it adds the important constraint that trade_date is mutually exclusive with start_date/end_date. It also lists output fields, adding context beyond the input schema.

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

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

The description clearly identifies the tool as providing Dragon-Tiger List (institutional seats) market data, which is a specific resource and distinguishes it from the sibling top_list (general top list). It lacks an explicit verb but the intent 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 explicitly states the PRO package requirement and the mutual exclusion between trade_date and start_date/end_date, providing actionable usage constraints. It does not explicitly contrast with alternatives like top_list, but the institutional-seat qualifier implies a distinct use case.

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?

Since no annotations are provided, the description carries the full burden and does well: it discloses the PRO subscription requirement, the 403 error behavior, the mutual exclusivity of trade_date versus start/end_date, and the return format. It does not mention rate limits or pagination, but for a read-only data tool the disclosed traits are adequate.

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

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

The description is short and structured with an Args/Returns format, making it easy to scan. The opening phrase is a fragment rather than a full sentence, but every part conveys essential information: purpose, subscription requirement, parameters, and return fields.

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

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

The description provides return field names and parameter constraints, but it is ambiguous whether a symbol is required or if queries without a symbol are valid, since all parameters are optional in the schema. The tool's query modes are not fully specified, which could lead to incorrect 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 description's Args section exactly repeats the parameter descriptions already present in the input schema (100% coverage). The description adds no new meaning beyond what the schema 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 clearly identifies the tool as providing Dragon-Tiger List (龙虎榜) individual stock market data, and the return fields clarify it is a data retrieval tool. However, it lacks an explicit verb like 'get' or 'list' and does not distinguish itself from sibling tools such as top_inst or limit_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 gives no guidance on when to use this tool versus alternatives. It only mentions the PRO subscription requirement and a 403 error for lower tiers, which is a prerequisite, not usage guidance 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?

With no annotations, the description discloses access-level failure (403) and exact matching behavior for symbol, plus the return format. It does not explain behavior when filters are omitted or combined, or whether the operation is read-only (though that is inferable).

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

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

The description is compact and uses clear Args/Returns sections. It is slightly redundant ('ETF' repeated in parentheses) and the Args block duplicates schema data, but it remains well-organized and front-loaded.

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 4-optional-param lookup with no annotations. The description gives essential return fields and a permission note, but lacks guidance on parameter combinations, tool selection among index-related siblings, and behaviors like pagination or empty results.

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

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

Schema description coverage is 100%, and the Args section mirrors the schema descriptions exactly. No additional semantic detail is provided about optionality, date range interactions, or valid symbol types beyond what the schema already states.

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

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

The description clearly identifies the resource as ETF tracking index information and enumerates the returned fields. However, it uses a noun phrase rather than an explicit verb like 'query' or 'list', and does not explicitly differentiate from sibling index/ETF 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 by naming the resource and includes a plan prerequisite ('Starter or above, otherwise 403'), but it does not explicitly state when to prefer this tool over siblings like etf_daily or index_weight, nor any 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?

With no annotations, the description carries the burden. It discloses that SSE is the default exchange and specifies the return fields (exchange, cal_date, is_open, pretrade_date), adding some context. However, it omits other behavioral traits such as valid date ranges, error handling, or whether start/end are required together.

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

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

The description is compact and structured, listing parameters and return fields. However, the Args section duplicates schema information, which is unnecessary but not overly verbose.

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 presence of an output schema and the simplicity of a calendar lookup, the description is mostly complete, but it lacks usage context and deeper behavioral notes. The default exchange note is helpful, yet the tool would benefit from clarifying parameter dependencies.

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 parameters, so the baseline is 3. The description's Args section merely repeats the schema's descriptions without adding new meaning, constraints, or examples.

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 identifies the tool as a trading calendar data source ('交易日历') with default SSE exchange and basic info, which clearly indicates it provides trading calendar data. It lacks an explicit verb like 'list' or 'query', but the resource is unambiguous and distinct from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool vs alternatives. It does not reference any sibling tools or conditions for use, leaving the agent to infer from the name alone.

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