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 indicates a read-only operation ('获取') but does not disclose other behavioral traits like pagination, rate limits, or dependencies. The description is adequate but lacks depth.

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

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

The description is a single sentence that efficiently enumerates the data types. It is not overly verbose, though a clearer separation of items (e.g., bullet points) could improve readability. It avoids fluff.

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

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

Given the tool has 7 parameters (1 required) and no output schema, the description covers the core purpose and parameter options but lacks usage guidelines and behavioral details. It is moderately complete but could benefit from additional context.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the meaning of each info_type value and providing context for parameters like exchange and market with specific options, going beyond the schema's brief descriptions.

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

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

The description clearly states it retrieves basic information data with specific types (stock lists, trade calendars, etc.) and uses a strong verb-resource pair. It distinguishes itself from sibling tools that focus on more specific data like stock_data or index_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 does not provide any guidance on when to use this tool versus alternatives. It lists the types of data but does not explain scenarios where basic_info is preferable to more specialized sibling tools.

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

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

No annotations are provided, so the description must carry the full burden. It uses '获取' (get) to imply a read operation, but does not disclose potential side effects, permissions, or data volume. Adequate but not thorough.

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

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

The description is a single, well-structured sentence that front-loads the purpose. Every word contributes meaning, and there is no redundancy or fluff.

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

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

Given no output schema and no annotations, the description provides basic context but does not explain return format, pagination, or data limits. It is incomplete for a tool that likely returns large datasets.

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

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

Schema description coverage is 100% (all three parameters have descriptions). Per guidelines, when coverage is high, baseline is 3. The description adds no additional parameter information beyond the schema, so no extra value.

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

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

The description clearly states the tool retrieves block trade data ('获取大宗交易数据') and lists specific details like price, volume, and trading parties. It distinguishes from siblings like 'stock_data' or 'margin_trade' which cover different data types.

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

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

The description does not explicitly state when to use this tool versus alternatives. It implies it is for block trade queries, but lacks guidance on context or exclusions, which reduces its helpfulness for an AI agent deciding between siblings.

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

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

No annotations are provided, so the description must disclose behavioral traits. It fails to state whether the tool is read-only, has rate limits, or requires authentication. It only lists data types and export options, without 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 a single long sentence that enumerates many items, which is not concise. It could be better structured with bullet points or separate lines. However, it does front-load the main 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 complexity (7 parameters, many data types), the description lacks completeness. It does not explain the differences between similar data types (e.g., balance_basic vs balance_all) or the return format when output_format is not specified. No output schema to compensate.

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

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

Schema coverage is 100%, so the schema already describes all parameters. The description adds a list of data types and notes export formats, but these are largely redundant with the parameter descriptions. No significant 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 it retrieves comprehensive performance data of listed companies, listing specific data types and export formats. It distinguishes from siblings like HK and US versions by implication (ts_code format for A-shares).

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

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

No guidance on when to use this tool vs alternatives (e.g., company_performance_hk, company_performance_us). No mention of prerequisites, context, or when not to use. The description only lists capabilities.

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. It only states the tool retrieves data, which implies a read operation, but does not disclose any behavioral traits such as authentication requirements, rate limits, data freshness, or pagination. For a financial data tool, additional context about data availability or constraints would be helpful.

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?

Description is a single, front-loaded sentence that covers the core functionality without extraneous content. Every word is necessary. It is appropriately sized 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?

Given the absence of an output schema, the description does not clarify the return format. It mentions the data types but not the structure or period granularity. The schema descriptions are thorough, but the overall context is minimally sufficient for an agent to use the tool correctly. Some gaps remain, such as expected data range or examples.

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

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

Schema coverage is 100%, so the schema already documents all parameters. The description adds no additional meaning beyond the schema; it only mentions the types of financial statements, which are already reflected in the 'data_type' enum. Baseline 3 is appropriate as the description does not degrade parameter understanding but adds no extra value.

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

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

Description clearly states it retrieves comprehensive performance data for Hong Kong listed companies, including income statements, balance sheets, and cash flow statements. The verb '获取' (get) and resource '港股上市公司综合表现数据' are specific. The sibling tools 'company_performance' and 'company_performance_us' indicate geographic differentiation, and the tool name includes 'hk' to disambiguate.

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?

Description provides no explicit guidance on when to use this tool versus siblings. It does not mention alternatives or scenarios where this tool should not be used. The context of 'hk' in the name implies it's for Hong Kong stocks, but the description itself lacks any comparative or exclusionary language.

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 that the tool returns performance data including financial statements and indicators, which suggests a read operation. However, it does not detail any behavioral traits such as rate limits, authentication requirements, or response format (no output schema).

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

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

The description is a single, efficient sentence that directly states the tool's purpose. It is front-loaded with the main function and contains no unnecessary 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?

The tool has 5 parameters with full schema descriptions, and the description lists the types of returned data. This is adequate for an agent to understand the tool's capability. However, it does not explain the optional 'period' parameter's effect beyond what the schema provides, but the schema already covers it. The description is complete enough for a data retrieval tool of moderate complexity.

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

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

Schema description coverage is 100% as each of the 5 parameters has a description in the schema. The description does not add extra meaning beyond what is in the schema—it merely reiterates the data types. 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 specifies '获取美股上市公司综合表现数据' (get comprehensive performance data of US-listed companies) and lists specific data types (income statement, balance sheet, etc.). This clearly identifies the tool's function and distinguishes it from siblings like 'company_performance' and 'company_performance_hk' through the explicit '美股' (US stocks) reference.

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

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

The description implies usage for retrieving US stock performance data, but does not provide explicit guidance on when to use this tool versus alternatives (e.g., when to use 'company_performance_hk' for Hong Kong stocks). No exclusions or when-not scenarios are mentioned.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It states the tool retrieves data (non-market), implying read-only behavior, but does not explicitly confirm safety, rate limits, or any side effects. This is insufficient for a query tool with no annotation support.

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

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

The description is two sentences, front-loading the main purpose and enumerating two query methods without redundant words. Every sentence serves a purpose, making it concise and easy to parse.

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

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

Given the tool's moderate complexity (4 parameters, no output schema), the description covers the two query patterns and parameter dependencies. It does not describe return format or pagination, but the scope is limited enough that this is acceptable. The presence of detailed schema descriptions partially compensates for omitted output details.

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?

With 100% schema description coverage, baseline is 3. The description adds value by explaining how parameters relate to the two query modes: issue type uses start_date/end_date, info type uses ts_code. This contextual mapping enhances understanding beyond the schema's individual parameter descriptions.

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

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

The description clearly states the tool retrieves 'convertible bond non-market data' and explicitly lists two query methods (issue type by time range, info type by code). This specific verb+resource+scope distinguishes it from sibling tools, which focus on stocks, indices, or general financial data.

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

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

The description explains the two internal query modes (issue and info) and when each should be used (issue for time-range queries, info for code queries). However, it offers no guidance on when to use this tool versus sibling tools (e.g., stock_data for market data). This lack of external comparison limits the score.

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 for behavioral disclosure. It describes the data returned (market data, weights, financial metrics) but does not address read-only nature, destructive potential, rate limits, or data freshness. The description is transparent about the output content but lacks behavioral warnings or constraints beyond the stated purpose.

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

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

The description is a single sentence that efficiently conveys the tool's purpose and the extensive list of output metrics. While compact, it could benefit from structuring the financial metrics as a bulleted list for readability. No redundant information is present, and the key action verb 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?

Given the complexity (multiple output metrics per constituent) and absence of an output schema, the description adequately lists the financial metrics but does not explain the output format (e.g., time-series vs. snapshot, per-constituent structure). The tool likely returns a table of constituents with weights and metrics, but this is not clarified. More detail on the data shape and temporal behavior would improve completeness.

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

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

Schema coverage is 100% with each parameter described. The description adds value beyond the schema by clarifying that index_code is limited to CSI indices (including industry/theme) and lists accepted formats (e.g., .SH/.SZ, sh000300, sz399006). It also specifies that the tool provides detailed financial metrics, which helps agents understand what the parameters will yield.

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 precisely states the tool retrieves CSI index constituents data including market quotes, weights, and a comprehensive list of financial metrics. It clearly differentiates from sibling tools like stock_data (individual stocks) and index_data (pure index values) by specifying CSI-specific constituents with detailed valuation and financial summaries.

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?

Description implies use for CSI index constituent data but provides no explicit guidance on when to use this tool versus alternatives (e.g., index_data for broader index information, stock_data for individual stocks). No when-not-to-use or exclusion criteria are stated, leaving the agent to infer usage context from the purpose.

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 specifies the timezone and that the output includes year/month/day/hour/minute/second. No side effects or additional traits needed for a simple read tool. Could mention it's non-mutating but acceptable.

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

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

Single sentence, front-loaded with key info (timezone and what it returns). 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 simplicity (1 optional param, no output schema), the description is fully complete. It covers the return value and timezone, no gaps.

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

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

Schema coverage is 100% and schema describes the format parameter. The description adds context about timezone and full datetime info, which enhances understanding beyond the schema's enum list.

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 the current timestamp in East Eight Zone (China time zone) with full datetime info, using a specific verb '获取' and resource '时间戳'. It is distinct from sibling tools which are all financial data tools.

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

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

No explicit when-to-use or when-not-to-use guidance is provided. However, the context of sibling tools (all financial) implies it's for general timestamp needs. Lacks alternative suggestions or exclusions.

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

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It does not mention rate limits, data freshness, authentication requirements, or any side effects. The description only states what data is returned, leaving the agent unaware of potential constraints or behaviors.

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 (two sentences) and front-loaded with the key purpose and parameters. It avoids unnecessary words. However, it could be slightly more structured by separating required and optional parameters more clearly, but it remains 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 has only two parameters and no output schema, the description provides adequate context: purpose, required/optional parameters, and return content. However, it lacks usage guidelines and behavioral transparency, which are gaps for a tool that might involve rate limits or authentication. Overall, it meets minimum viability but is 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?

Schema coverage is 100%, with both parameters described. The description adds context by explicitly marking trade_date as required and ts_code as optional, and it explains the return fields (buy/sell/net amounts, reasons). This goes beyond the schema, which only provides type and format for trade_date.

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: institutional transaction details of the 'dragon and tiger' list (top_inst). It identifies the required and optional parameters and outlines the return content (buy/sell/net amounts, reasons). This distinguishes it from sibling tools that cover general stock data or other financial metrics.

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 required and optional parameters but provides no guidance on when to use this tool over siblings. There is no discussion of context, prerequisites, or alternative tools for similar queries. The user must infer usage from the purpose alone.

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

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It mentions using a 'real search API' and 'intelligent search', but lacks details on rate limits, pagination, result count, historical range, or any side effects. This vagueness leaves agents uncertain about important behavioral traits.

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

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

The description is a single concise sentence in Chinese that effectively communicates the main purpose and capability. It is front-loaded and contains no redundant information, earning its place 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?

Given the tool has only one parameter and no output schema, the description provides adequate context about what it does and the data source. However, it lacks information about return format, result limits, or when not to use it, leaving some gaps for a search 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 single required parameter 'query' has a detailed description in the schema with examples and explanation of keyword usage. The tool description adds value by specifying the API source ('real search API') and the media type ('mainstream financial media'), complementing the schema's coverage.

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

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

The description clearly states that the tool retrieves news content from mainstream financial media via a real search API, supporting single or multiple keyword searches. This is specific and distinct from sibling tools like hot_news_7x24 (real-time hot news) and basic_info (basic information), making its purpose unambiguous.

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

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

The description implies usage for keyword-based search of financial news but does not explicitly state when to use it versus alternatives like hot_news_7x24 for real-time news or other tools. No exclusions or prerequisites are mentioned, so guidance is only implicit.

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 lists supported data types and output formats, implying read-only behavior. However, it does not explicitly state that it is read-only or mention any side effects, rate limits, or pagination. The description is adequate but not exhaustive.

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

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

The description is a single sentence, very concise, and front-loaded with the core functionality. It covers the main purpose without unnecessary words. Every part is earned, although it could be slightly expanded to include important caveats.

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 (7 parameters, 1 enum, no output schema), the description is incomplete. It does not explain return value structure, data formats, or potential performance implications. The schema partially fills gaps with parameter descriptions, but the description lacks overall context for an AI agent to use it effectively.

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 parameters are described in the schema with complete coverage. The description adds little beyond the schema, merely summarizing data types and output formats. Since schema coverage is 100%, baseline is 3; the description does not significantly enhance parameter understanding.

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

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

The description clearly states the tool retrieves comprehensive fund data and lists specific data types (fund list, managers, NAV, dividends, holdings). It distinguishes itself from sibling tools like stock_data or company_performance by focusing specifically on public offering funds.

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 does not provide explicit guidance on when to use this tool versus alternatives. It lacks information about prerequisites, handling large datasets, or fallback options. While the schema includes a note about large data for certain types, the description itself does not guide 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 must disclose behavioral traits. It mentions the returned information but does not cover error handling, data freshness, or any side effects. The description is adequate for a simple read query but lacks depth.

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

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

The description is a single concise sentence in Chinese that front-loads the purpose. It is efficient but could be slightly more structured (e.g., bullet points) 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?

Given the absence of an output schema, the description provides a high-level overview of returned fields. It is adequate but does not mention handling of empty results, pagination, or errors. Slightly more detail would improve completeness.

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 does not need to re-explain parameters. It does not add any additional meaning beyond the schema descriptions for 'name' and 'ann_date'. 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 states the tool queries fund manager details by name, including specific outputs like managed fund list, personal background, and work experience. It distinguishes from sibling tools which focus on different financial data types.

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

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

The description implies usage when querying fund manager details by name but lacks explicit guidance on when to use this tool versus alternatives or any preconditions or exclusions.

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

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

No annotations provided, so description must carry full burden. It mentions fetching from Tushare and content similarity dedup, but fails to disclose rate limits, data freshness, authentication needs, or any destructive 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?

Single, front-loaded sentence with no wasted words. Efficiently communicates the tool's purpose and scope.

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 one simple parameter and no output schema. The description covers basic purpose but lacks details about return format or expected output structure, which would be helpful for a news-fetching 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% for the single parameter 'limit'. The description adds no additional meaning beyond the schema, which already explains default, upper bound, and dedup behavior. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool fetches hot news from Tushare news interface across multiple categories. It uses a specific verb ('获取') and resource ('新闻'), but does not explicitly differentiate from sibling tools like finance_news, which may be a subset.

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 alternatives like finance_news or basic_info. Missing information about prerequisites, limitations, or scenarios where this tool is 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?

No annotations are provided, so the description must carry the burden. It only states basic functionality (retrieve data, export formats) but omits details like read-only nature, required permissions, error behavior, or data structure returned. This is insufficient for a full behavioral understanding.

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

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

The description is a single, concise sentence that front-loads the primary purpose. It efficiently conveys core information without extraneous details, though it could benefit from structured presentation of key points.

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 lacks information about the return value or output format beyond mention of CSV/JSON export. Without an output schema, the agent does not know what data fields (e.g., OHLCV, date) are returned. This is a significant gap 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 coverage is 100% and parameters are well-described in the schema. The description adds minimal additional value beyond examples (code format, export types). Since schema already documents parameters, a baseline score of 3 is appropriate.

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

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

The description clearly states the tool retrieves data for a specified stock index, provides examples (Shanghai Composite, Shenzhen Component), and mentions export formats. This effectively distinguishes it from sibling tools like stock_data (individual stocks) and fund_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?

No guidance is provided on when to use this tool versus alternatives. While the name implies index data usage, there is no explicit comparison to sibling tools or mention of exclusions. The agent must infer context from the title alone.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It fails to mention key traits: whether data is real-time or historical, rate limits, authorization needs, or how the markdown default output works. The mention of export formats is helpful but insufficient.

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

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

The description is a single sentence that efficiently communicates purpose and supported indicators. It could be better structured with more front-loaded key points, but it avoids wordiness.

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 retrieves multiple macroeconomic indicators with 5 parameters and no output schema, the description lacks completeness. It does not explain return values, pagination, data volume, or how results are structured. Crucial context for an agent to use this tool effectively is missing.

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

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

Schema description coverage is 100% with detailed parameter descriptions. The tool description lists example indicators but does not add meaningful beyond what the schema already provides. 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 retrieving macroeconomic data, enumerating a comprehensive list of indicators (Shibor, LPR, GDP, CPI, etc.), and explicitly states support for CSV/JSON export. This distinctively separates it from sibling tools focused on stock, fund, company, or other specific 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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, limitations, or scenarios where this tool is preferable to others like stock_data or finance_news.

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 full burden. It only states the basic function of getting data, without disclosing behavioral traits such as read-only nature, rate limits, authentication requirements, or error handling. This is insufficient for a tool with multiple parameters and data types.

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

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

A single sentence that is concise and front-loaded with the main purpose. It efficiently lists supported data types, though a bulleted list could improve readability. 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?

The tool has 5 parameters and no output schema. The description does not explain return values, pagination, or how to interpret the data types. For a data retrieval tool, this is a significant omission, leaving the agent without guidance on what to expect from the response.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds a high-level categorization of data types ('融资融券标的股票、交易汇总、交易明细等'), which helps group parameters but does not add syntax or format details beyond what the schema already provides for each parameter.

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

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

The description clearly states the tool retrieves margin trading data ('获取融资融券相关数据') and lists multiple data types (标的股票、交易汇总等). The title 'Margin Trade' aligns. It distinguishes from sibling tools by focusing on a specific financial domain not covered by others like basic_info or stock_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?

No explicit guidance on when to use this tool versus alternatives is provided. The description implies usage for margin trading data, but it does not mention when not to use it or suggest other tools for related data needs.

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 exist, so the description must fully disclose behavior. It lists data types but omits key traits: read-only nature, data granularity (daily?), rate limits, authentication needs, and error handling. The description is inadequate for a tool with no annotation support.

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

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

The description is a single concise sentence that front-loads purpose and includes details on data types. However, it could be slightly clearer by separating purpose from data items.

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

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

With no output schema, the description should explain return format and data frequency. It describes the data fields adequately but misses behavioral context like read-only and update timing. Adequate but not 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%, baseline 3. The description adds value by explaining that omitting ts_code queries market-level data, which clarifies the optional parameter. However, it does not elaborate on date format beyond the schema.

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

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

The description clearly states the tool retrieves capital flow data for individual stocks and market, specifying the types of flows (主力, 超大单, etc.). It distinguishes from siblings like stock_data or index_data by focusing on money flow specifically.

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 via ts_code optionality for stock vs market, but lacks explicit guidance on when to use this tool versus alternatives like stock_data or margin_trade. No exclusions or when-not-to-use are provided.

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

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

With no annotations provided, the description is the sole source of behavioral transparency. It does not disclose data source freshness (real-time vs. delayed), rate limits, or whether the tool is read-only. The mention of 'via Binance' for crypto hints at a specific source but lacks 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 a single, concise sentence that efficiently communicates the core action and scope. It is front-loaded and to the point, with 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 complexity (7 parameters, multiple markets, no output schema), the description is incomplete. It fails to explain return formats, data granularity (daily, hourly?), or any limitations. The comprehensive schema partially compensates, but the description leaves gaps.

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

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

Schema coverage is 100%, so the individual parameter descriptions in the schema are already comprehensive. The tool-level description adds no extra parameter context beyond summarizing the tool's purpose. Thus, a baseline score of 3 is appropriate.

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

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

The description clearly states the tool retrieves historical market data for stocks and crypto assets, listing supported markets (A股, 美股, etc.). It is specific about the verb and resource but does not differentiate from sibling tools like stock_data_minutes, which may imply a different granularity.

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

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

No explicit guidance on when to use this tool versus alternatives such as basic_info, fund_data, or stock_data_minutes. The description does not mention any prerequisites or exclude scenarios, leaving the agent to infer usage.

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 cover behavioral traits. It states the tool fetches K-line data but does not mention side effects, rate limits, response format, or that it is a read-only operation. The description adds minimal 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 a single, clear sentence with no wasted words. It is appropriately concise and front-loaded with the key action.

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 lacks information about the output shape (e.g., OHLCV fields), which is critical for a data retrieval tool with no output schema. It also omits any guidance on pagination or limits, making it incomplete.

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

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

Schema coverage is 100% with descriptions. The tool description repeats frequency support and datetime requirement already in the schema, adding no new meaning. Baseline score of 3 is appropriate.

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

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

The description clearly states it gets minute K-line data for A-shares and crypto with specific frequencies. It effectively distinguishes from sibling tools like stock_data (likely daily data), but explicit differentiation would be stronger.

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 need for start/end datetime but provides no guidance on when to use this tool versus alternatives (e.g., stock_data for daily data) or exclusions.

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