A股数据 API (A-Share Data API)

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It mentions the data returned but does not state whether the operation is read-only, how invalid codes are handled, or any side effects. The example code hints at usage but does not explain behavior beyond the data content.

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

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

The description is a single concise sentence that front-loads the purpose and the key metrics. There is no wasted text, though the example could be more structured. It is efficient but not fully elaborated.

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 that an output schema exists (as per context signals), the description need not explain return values. It lists the specific metrics, which is useful. However, it lacks any usage context, such as how to obtain the code or when to prefer this tool. For a single-parameter tool, it is mostly adequate but leaves the agent with 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 description coverage is 0%, so the description must compensate. It gives a concrete example 'code=sh113052', implying the code is the convertible bond identifier. This is helpful but not explicit; it does not fully define the parameter format or accepted values.

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 convertible bond terms, listing specific metrics (premium rate, double low, strong redemption trigger price, conversion price). The resource (convertible bonds) and the kind of data are explicit, though it does not differentiate from sibling tools or state a verb like 'get'.

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 like ashare_quote or ashare_kline. There is no mention of context, prerequisites, or exclusions, so the agent must infer when this is the appropriate choice.

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

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

With no annotations provided, the description carries the full behavioral disclosure burden. It does disclose one meaningful behavioral trait: '免费工具（无需 Key）' states that no API key is required, which addresses authentication expectations. However, it does not mention whether the tool is read-only, whether data is delayed, or any limits, though the zero-parameter and output-schema presence reduce the risk. The disclosure is minimal but not absent.

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 very concise, with the core purpose front-loaded and the free/no-nejmensaje requirement appended cleanly. Every phrase adds some value: the topic, the parenthetical scope, the market-breadth label, and the Key-free note. It could be slightly more informative about usage context, but for a zero-parameter tool it is 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 zero-parameter tool with an output schema, the description does not need to explain return values, so the lack of that detail is acceptable. What is missing is guidance on when this tool should be preferred over overlapping siblings such as ashare_market_overview or ashare_hot. The free/no-key note adds operational context, but the overall description is just enough to identify the tool, not fully complete for routing an agent to the correct tool among similar ones.

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

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

The tool has zero parameters patible with an empty schema, so the baseline is 4 even without parameter detail in the description. The description does not need to explain parameter semantics because there are none to explain. The mention of '涨跌分布……成交额' adds context about what the returned data represents, which indirectly helps an agent understand the no-parameter call.

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's resource as '涨跌分布' (rise/fall distribution) and defines its scope with parenthetical details: rise/fall counts, limit-up/down, turnover, and market breadth. It does not use an explicit verb like 'get' or 'query', but the noun phrase plus explanation makes the purpose understandable. It doesn't explicitly distinguish this from siblings like ashare_market_overview, but the market-breadth framing is a distinctive clue.

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-related context by saying it is a free tool requiring no Key, which implies it can be used without authentication. However, there is no guidance about when to choose this tool over sibling tools such as ashare_market_overview or ashare_hot, and no exclusions or alternative conditions. The when-to-use guidance is essentially absent.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only explains mode semantics and does not reveal behaviors such as data scope, freshness, whether symbol is required for detail mode, or any effects. This is a minimal amount of behavioral context 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 very short and front-loads the resource, but it is under-specified rather than optimally concise. Every sentence earns its place, yet the terse style leaves important context about parameters and usage unstated.

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 that an output schema exists, return value details are not required, but the description still lacks essential context: what 'list' vs 'detail' returns, how limit and symbol interact with each mode, and when this tool is appropriate among 20+ siblings. The tool is simple, but the absence of param semantics and usage guidance makes 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 description coverage is 0%, so the description must compensate. It does clarify the meaning of the mode parameter (list vs detail), but says nothing about limit or symbol. With three parameters totally undocumented in the schema, describing only one is insufficient.

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 a specific resource—broker research report summaries ('脱水研报（券商研报摘要）')—and the tool's purpose is clear enough to distinguish it from siblings like ashare_quote or ashare_finance. It lacks an explicit verb and does not explicitly differentiate itself from sibling tools, but the resource is concrete and meaningful.

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 that mode=list provides a list and mode=detail provides details, but gives no guidance on when to use this tool versus sibling tools such as ashare_events, ashare_finance, or ashare_sector. There are no alternatives named and no exclusions or contextual conditions described.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states a subject ('dividend and split history') without indicating whether the operation is read-only, what data it returns, any limits (like number of years), or side effects. The description is a bare phrase and provides no behavioral transparency at all.

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 short, which is concise, but it is under-specified to the point of being incomplete. It is a fragment rather than a structured sentence, and it omits essential information about usage and parameters. This is not effective conciseness; it is a lack of specification.

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 two parameters, the large set of sibling tools, and the absence of annotations, the description is woefully incomplete. It does not explain what the tool returns, how to use it, or how it relates to siblings. The presence of an output schema reduces the need to describe return values, but the description still fails to provide the basic context needed for correct tool selection and invocation.

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

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

Schema description coverage is 0%, so the description must compensate for the undocumented parameters 'code' and 'years'. However, the description does not mention either parameter or explain that 'code' is a stock identifier and 'years' is a time span. It provides minimal context about the domain but fails to add meaningful semantics beyond the schema.

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

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

The description '分红送转历史' conveys that the tool returns dividend and stock split history, but it is a noun phrase with no explicit verb or action. It identifies the resource clearly but does not distinguish it from siblings like ashare_finance or ashare_events, which could also cover dividend data. The purpose is vaguely stated but inferable.

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 does not mention any conditions, exclusions, or sibling tools. There is no explanatory context that would help an agent decide to choose ashare_dividend over other ashare_* tools.

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

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does reveal that the tool provides an overview with specific metrics and implies a read-only snapshot, but it does not mention data scope, freshness, rate limits, or response behavior beyond what the output schema already supplies.

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 compact line with no filler. The core purpose is front-loaded, the metric scope is parenthetically specified, and the parameter example earns its place by making the schema more actionable.

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

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

For a one-parameter tool with an output schema, the description provides sufficient context: the resource, the key metrics covered, and a realistic code example. It lacks explicit guidance on when to choose this tool over sibling tools, but that gap is already accounted for in usage_guidelines.

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 0% schema description coverage, the description compensates by giving a concrete example, 'code=sh510300', which clarifies the expected string format for an exchange-prefixed ETF code. It does not exhaustively document valid formats, but for a single obvious parameter this example adds real value beyond the bare 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 resource (ETF) and the purpose (概览/overview), and specifies the included dimensions: 规模/溢折率/资金流. This distinguishes it from broader siblings like ashare_quote or ashare_fund, though the distinction is not stated explicitly.

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

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

No explicit guidance is given about when to use this tool versus alternatives such as ashare_fund or ashare_quote. The only usage hint is the example 'code=sh510300', which demonstrates the parameter but does not explain selection criteria 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 must carry the behavioral disclosure burden. It only states that the tool returns event labels; it does not mention whether it is read-only, data freshness, pagination, authentication needs, or response structure. This is a minimal 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 extremely concise, front-loading the core purpose and adding a useful category list. It wastes no words, though it is a noun phrase rather than a complete sentence, which slightly reduces 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 low complexity (1 parameter) and presence of an output schema, the description could be minimal, but it omits critical information such as the time range, event categories' exact meanings, or how to interpret the returned tags. It is not sufficiently complete for an agent to call the tool confidently without external knowledge.

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 0% and there is one required parameter, 'code'. The description does not explain the code format, exchange requirements, or stock universe, leaving the parameter ambiguous despite the '个股' hint. The description adds no meaningful parameter-level guidance beyond the schema's bare type.

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 individual stock event tags and enumerates 42 categories with examples (block trades, dragon-tiger list, buybacks, dividends, share unlocks). This conveys the tool's scope and distinguishes it somewhat from specific event siblings like ashare_lhb and ashare_dividend, though it lacks an explicit verb and direct sibling differentiation.

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

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

There is no guidance on when to use this tool versus the specific event tools (e.g., ashare_lhb for dragon-tiger list, ashare_dividend for dividends). The description provides no context for selection, prerequisites, or alternatives.

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

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only names the data category and trigger phrases; it does not disclose read-only behavior, output format, number of periods, or any limitations. This leaves an agent without insight into what actually happens when the tool is invoked.

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 tight: the first sentence states the resource, and the second sentence gives concrete user-query triggers. Every clause earns its place, with no filler or repetition.

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

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

An output schema exists, so return value details may be covered there, and the purpose plus trigger usage are present. However, with no parameter semantics and no behavioral context, the description is not fully self-sufficient for an agent choosing and invoking 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 0%, and the description provides no explanation of 'code' or 'num'. The agent is left to guess what format the stock code should take and what the defaulted 'num' means, which is a critical gap for correct invocation.

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: financial statements (income statement, balance sheet, cash flow statement). It does not use an explicit verb like 'returns' or 'retrieves', but the scope is unmistakable and the mention of specific report types helps distinguish it from the many sibling ashare_* tools.

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

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

The description explicitly states when to use the tool: when users ask about revenue, net profit, liabilities, or financials. This is clear context for triggering, though it does not mention when not to use it or name alternative 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 provided, the description carries the full burden of behavioral disclosure DNA. It names the data categories but does not state whether the operation is read-only, what the returned data covers, or any limitations or freshness considerations. This is a meaningful gap for an unannotated 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 one compact sentence that front-loads the core data categories and immediately follows with concrete user query triggers. There is no filler or redundancy.

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

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

The description covers the primary use case and the tool has an output schema, so return-value documentation is not strictly necessary. However, the parameter semantics are underspecified for a single required code parameter, and the overlap with ashare_lhb is not resolved, leaving some 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?

The schema provides only a 'code' parameter with 0% description coverage, and the description does not explain the expected format, meaning, or possible values of 'code'. An agent can infer it likely refers to an A-share stock code from the tool context, but the description adds no explicit parameter guidance.

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 comprehensive financial data tool covering funds flow, Dragon-Tiger List, block trades, and margin trading, and maps it to specific user query topics. However, it does not explicitly distinguish itself from the dedicated sibling ashare_lhb, so the differentiation is somewhat implicit.

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

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

The description gives explicit user-query signals ('主力资金/龙虎榜/机构动向/融资融券') for when to select this tool. It does not provide exclusions or mention when a sibling like ashare_lhb should be used instead, which would make the guidance fully complete.

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 carries the burden of behavioral disclosure. It adds useful context that the tool is free and requires no API Key, and it clarifies the market scope (A-share/US/ETF). It does not describe ranking recency or sorting semantics, but the read-only nature is reasonably apparent from the hot-list framing.

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 very compact: it front-loads the resource and use case in the first clause, then adds only the relevant no-key note. There is no filler or repetition.

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

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

For a tool with one optional parameter and an output schema, the description covers the market scope, user intent, and authentication requirements. The only notable gap is that `limit` is left undocumented, though its name and default mitigate the 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?

The only parameter, `limit`, has zero schema description coverage and the description never mentions it. The English name and default value of 30 make it partially self-explanatory, but with 0% coverage the description should have compensated and did not.

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

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

The description names a specific resource: a hot-search list for A-shares, US stocks, and ETFs, and connects it to a concrete user intent ('什么股票热门/大家在看什么'). It lacks an explicit verb like 'returns' or 'lists', but the noun phrase plus usage intent is clear and distinguishes it from the sibling ashare_* 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 gives a direct trigger condition: use this when users ask which stocks are hot or what everyone is watching. It gives clear context for when to invoke the tool, though it does not explicitly name alternatives or state 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, the description carries the behavioral disclosure burden. It states what kind of data is returned (IPO event calendar), which implies a read-only lookup, but it does not mention the time window, default behavior, or response format. This is adequate but thin.

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 very short, front-loaded with the core purpose, and every clause contributes. It loses some points because the omission of parameter context edges toward under-specification rather than mere conciseness.

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

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

For a single-optional-parameter read-only calendar tool with an output schema, the description covers selection and general intent well. The main gap is the undefined 'days' parameter, which prevents fully confident invocation without further reasoning.

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 0% and the description never mentions the single 'days' parameter. The bare integer with default 15 is ambiguous regarding units and direction, so the agent cannot confidently customize the calendar window.

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 precisely identifies the resource as an IPO calendar covering 发行/上市/中签 (issuance/listing/lottery), and explicitly ties it to user queries containing '新股/打新'. This clearly differentiates it from sibling ashare_* tools.

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

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

It gives an explicit trigger condition: use when the user asks about 新股/打新. However, it does not mention exclusions or alternatives among the sibling tools, so routing guidance is clear but not exhaustive.

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

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

There are no annotations, so the description carries the behavioral burden. It usefully discloses that the tool is free and requires no API key, and that it supports day/week/month periods. However, it does not mention data source, update latency, or any usage limits.

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 very compact: the tool's purpose, supported periods, triggering user intents, and no-key requirement are all conveyed in two short lines with no redundant wording.

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, and the description is sufficient for tool selection. However, the missing parameter documentation and lack of guidance on resolving stock names to A-share codes (e.g., via ashare_search) leave a clear invocation gap.

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

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

Schema description coverage is 0%, so the description must compensate, but it only hints that period relates to daily/weekly/monthly K-lines. It leaves the code format, count semantics, and exact period values undocumented, which is a significant gap for correct invocation.

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 (K-line data, daily/weekly/monthly) and maps it to concrete user intents like '走势/最近表现/历史K线'. It does not use an explicit verb or name alternative tools, so it stops short of full sibling differentiation.

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

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

The description explicitly states when to use the tool: when the user asks about trend, recent performance, or historical K-line data. It does not list exclusions or point to alternative tools such as ashare_quote for real-time quotes, but the trigger conditions are clear.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It does not state that this is a read-only lookup, any data limitations, date/market scope, or rate/authentication constraints, leaving the operation's behavioral profile mostly unspecified.

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

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

The description is one short front-loaded sentence: the resource is named first, followed by a compact key-value legend for the parameter. There is no filler or repeated schema information.

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

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

For a single-parameter tool with an output schema, the parameter semantics are complete enough to make a call. However, the lack of usage differentiation and any behavioral caveats leaves some context missing for an agent choosing among many sibling tools.

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

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

The schema provides only a plain string 'type' with 0% description coverage and no enum, so the description is the sole source of meaning. It defines all three valid values with Chinese labels (institution 机构榜, hotmoney 游资榜, activeseat 活跃席位), fully compensating for the schema gap.

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 the 龙虎榜 (Dragon-Tiger List) sub-list and enumerates its modes, so an agent can tell it is a categorized LHB lookup. It is clear, though it has no verb and does not explicitly contrast itself with sibling tools like ashare_hot.

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 type=... legend implies when to choose each variant (institution vs. hot money vs. active seats), but there is no explicit when-to-use or when-not-to-use guidance relative to the sibling ashare_* tools. An agent must infer applicability from the domain name 龙虎榜分榜.

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?

无注解提供，描述本身未披露任何行为特征（如是否只读、是否返回历史序列、是否受频率限制、输出格式等）。对调用后果完全无说明。

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?

单句极简，无冗余，但信息量严重不足。简洁本身是优点，但为了简洁牺牲了关键语义，导致实用性差，不达'每个句子都有价值'的标准。

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?

有输出schema但描述未提及，且对于2个参数（names、region）几乎无说明。作为宏观数据工具，应说明数据粒度、时间范围、命名规范等。当前描述完全不足以让agent正确调用。

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描述覆盖率为0%，描述仅提及region参数的可选值（cn/us/jp/eu/hk），但未解释names参数的含义或用法。描述未补偿schema的缺失，agent无法理解names的用途。

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?

描述列出具体宏观数据指标（GDP/CPI/PMI/LPR/国债收益率）并给出region可选项，明确了资源范围，但缺少动词（如'查询'/'获取'），且与同类工具（如ashare_bond）的区分不明显。虽非纯tautology，但目的表述偏泛。

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?

完全没有说明何时使用此工具、何时使用其他sibling（如ashare_market_overview、ashare_quote），也没有任何排除条件。仅列出region取值，对选择依据无帮助。

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

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

Annotations are absent, so the description carries the full disclosure burden. It does add one genuine behavioral/access trait beyond the schema — '免费工具（无需 Key）' (free tool, no Key needed) — which is valuable. But it does not state that the operation is read-only, mention data freshness/pagination, or describe any behavioral caveats for the six modes.

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

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

The description is compact and front-loaded: purpose first, then the parameter value map, then the use-case trigger, then the access note. Each sentence carries information with no filler. The dense type-value list is appropriate for a multi-mode tool, though it could arguably be structured more readably.

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

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

With only one parameter and an output schema present, the description covers the essentials for basic invocation. However, given 20 siblings and modes that overlap dedicated tools (technical vs ashare_technical, valuation vs ashare_sector_valuation), it does not clarify when the overview tool's modes should be chosen over those siblings — a notable gap for correct tool selection.

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

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

The schema provides only a bare 'type' string parameter with a default and no enum, and description coverage is 0%. The description compensates fully by enumerating all six valid values and their meanings (summary=画像总评, trade=收盘, interval=多周期, technical=大盘技术, updown=涨跌分布, valuation=估值分位, rotation=风格轮动), which is essential information for an AI agent to invoke the tool correctly.

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

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

The description names a specific resource and purpose ('市场总览' — market overview) and enumerates six concrete modes (summary, trade, interval, technical, updown, valuation, rotation) with Chinese semantics. It is clearly distinct from siblings like ashare_quote or ashare_technical because it positions itself as the broad market-level overview, though it never explicitly names a sibling it is not.

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 an explicit trigger condition: '用户问今天市场怎么样用这个' (use this when the user asks how the market is today), which is clear usage context. However, it provides no exclusions or alternative routing — e.g., when to prefer ashare_technical over this tool's technical mode — so it stops short of full when/when-not guidance.

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

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

With no annotations, the description carries the transparency burden. It usefully discloses that the tool is free and requires no API key, and that it returns a real-time snapshot. But it doesn't mention potential limitations such as data delay, unsupported code formats, or behavior on invalid input. It's adequate for a simple read-only quote tool, 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 short, dense, and front-loaded with the core function before adding the use case and licensing note. Every clause contributes meaningful information with no redundancy.

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

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

The tool is simple and has an output schema, so return-value explanation isn't needed. The description covers what the snapshot contains, when to use it, and the fact that no key is required. However, the missing parameter format guidance is a meaningful gap that could prevent an agent from invoking 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 sole parameter `code` has zero schema description, and the tool description does not explain the expected format (e.g., 6-digit A-share code, HK ticker format, or prefix requirements). Since schema coverage is 0%, the description needed to compensate for this gap but does not.

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 real-time quote snapshot for A-shares/HK stocks, listing specific fields (current price, open/high/low, turnover amount, turnover rate). It also gives a concrete user-intent trigger, making the tool's function easy to identify. However, it doesn't explicitly distinguish it from sibling tools such as ashare_kline or ashare_market_overview.

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 clear usage condition: use when the user asks 'what price is a stock now'. This is practical and context-driven. It doesn't mention when not to use the tool or name alternative tools, so it falls short of full routing 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 explains the expression grammar and available factors, which clarifies behavior, but it does not state what the tool returns or its operational characteristics such as ordering and limits.

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 the purpose, then gives a useful example and field list. The field enumeration is long but earns its place for a domain-specific expression builder.

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 values need not be described. Still, the orderby and limit semantics are left to inference, and with many ashare sibling tools, explicit routing 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?

The required expr parameter is well explained with syntax, an example, and common field names. However, limit and orderby have zero schema description and are not addressed, so secondary parameters remain underspecified.

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 a factor-screening tool for A-share stocks ('因子选股（量化筛股）') and gives a concrete trigger intent ('筛选/选股/符合条件的股票'). It does not name sibling tools it is not, so it falls short of full differentiation.

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

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

The last sentence explicitly tells the agent when to invoke this tool: when the user asks to filter or find qualifying stocks. There is no explicit when-not-to-use or named alternative, but the trigger condition is clear.

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

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

No annotations are available, so the description carries the burden. It discloses that the lookup is fuzzy and disambiguates names to codes, but it doesn't describe behavior for multiple matches or no matches. For a non-mutating search tool, this is adequate but not rich.

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

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

The description is two short, dense clauses: purpose first, then usage. There is no filler, repetition, or restating of schema information.

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

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

For a one-parameter search tool with an output schema, the description covers what the tool does, what the input means, and when to invoke it. Not describing return values is acceptable because an output schema exists; slightly more detail on no-match behavior would make it fully complete.

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

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

The schema gives no description for q, so the description must compensate. It explains that q is a stock/fund/sector name supplied by the user and that matching is fuzzy, which is enough semantic context for the single 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 states a clear action—searching stocks/funds/sectors—and its purpose: fuzzy disambiguation to confirm a code when only a name is given. This differentiates it from the sibling quote, kline, and fund tools.

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

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

It explicitly says to use this tool first when the user supplies only a name, to confirm the code. It doesn't explicitly list when not to use it or name alternatives, but the '先用这个' (use this first) instruction implies it precedes other 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 provided, the description must carry the full burden of behavioral disclosure. It implies a read-only operation by calling it a '行情榜' (market ranking), but it does not explicitly state that it is non-destructive, has no side effects, or mention any rate limits or prerequisites. Since it is a simple data retrieval tool, the risk is low, but the description could be more explicit about its safety profile.

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, compact sentence that front-loads the resource and includes the usage trigger at the end. Every clause adds value, and it is easy to scan. No fluff or redundancy.

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

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

For a tool with no parameters and an output schema present, the description provides all essential information: what it returns (sector rankings with gains and leading stocks) and when to use it (rising sectors/rotation). The agent can decide to call it without needing 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?

The tool has zero parameters, and the schema is empty (100% coverage trivially). The description does not need to add parameter info. The baseline score for 0 parameters is 4, and the description does not detract from that; it adds context about what the tool returns (gains and leading stocks), which is helpful but not parameter-specific.

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 sector market ranking, specifying the resource (sectors) and the sub-categories (industry, concept, region) plus the leading stocks. It also provides a distinct trigger phrase ('哪些板块在涨/板块轮动'), which helps the agent distinguish it from sibling tools like ashare_sector_valuation or ashare_market_overview.

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

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

It explicitly states when to use the tool: when the user asks which sectors are rising or about sector rotation. This is a direct usage guideline, though it does not mention when not to use it or alternatives, the trigger conditions are precise enough to route the agent correctly.

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

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

No annotations are provided, so the description carries the burden. It discloses the output content (PE/PB/PS and historical percentile) and the code format, which is useful. However, it does not disclose whether this is a read-only operation, whether the data is point-in-time, or any rate limits or data freshness 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 two sentences, front-loading the core output (PE/PB/PS + historical percentile) and then giving a code example. Every sentence earns its place, though it could be slightly more structured.

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

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

The tool has one required parameter and an output schema, so the description is mostly complete for invocation. However, with no annotations and no guidance on how to obtain valid codes, an agent might struggle to construct a correct call. The example code helps but is not exhaustive.

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 0%, so the description must compensate. It explains the code parameter with an example format (pt01801780) and states it is a Shenwan sector code, which adds meaning beyond the bare schema. However, it does not explain the exact format pattern, whether the prefix is required, or how to find valid codes.

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

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

The description states a specific verb+resource: it provides sector valuation metrics (PE/PB/PS) plus historical percentile. It distinguishes from siblings like ashare_quote and ashare_sector by specifying valuation metrics and historical percentile, though it doesn't explicitly name a sibling alternative.

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 context: it is for sector valuation data, and the example code format (pt01801780) gives a hint about the expected code type. However, it does not explicitly state when to use this tool versus alternatives like ashare_sector or ashare_quote, nor does it mention 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 provided, the description carries the full burden of behavioral disclosure. It only lists the data categories and gives usage triggers, but does not mention that this is a read-only lookup, any code format requirements, data freshness, or error behavior. This is minimal beyond the purpose statement.

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 tool's scope (shareholder research) and then supplies immediate usage triggers. Every clause adds value; no waste.

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

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

Given that an output schema exists and only one parameter is required, the description is mostly sufficient. The missing documentation of the 'code' parameter is the main gap, along with no explicit statement about the expected code format. These omissions prevent full 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?

The input schema has 0% description coverage, and the sole 'code' parameter is completely undocumented. The description does not mention the parameter at all, so it fails to clarify that 'code' refers to an A-share ticker. This is a critical gap for correct invocation.

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: shareholder research covering top ten shareholders, shareholder count, and institutional holdings. It also provides specific user-intent triggers ('who holds', 'shareholder changes', 'chips') that distinguish it from sibling tools like ashare_quote or ashare_finance.

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 tells agents to use this tool when users ask about 'who holds', 'shareholder changes', or 'chips'. It doesn't name alternative tools or state when not to use it, but the trigger-phrase guidance makes the usage context clear.

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

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

No annotations are provided, so the description carries the full burden. It only lists the indicators but does not disclose what the tool actually returns (e.g., whether it returns all indicators or just one, the format, whether it includes current values or historical data, or if it requires additional context like period). This is a significant gap for a tool that likely returns complex technical 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 very concise, only two short sentences. It front-loads the list of indicators and provides clear usage context. The only minor issue is that it could be slightly more descriptive about what it returns, but it is not verbose or 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?

The tool has an output schema, which may explain the return shape, but the description is still thin. It does not explain how the indicators are presented (e.g., as a combined report or separate series), nor does it clarify that omitted parameters use defaults. Given the complexity of technical indicators, more context (like whether it returns recent values or full history) would be helpful, but the presence of an output schema mitigates some of this.

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?

There is only one parameter, 'code', with no description in the schema (coverage 0%). The description does not mention the parameter at all, so it does not add meaningful semantics beyond the schema. However, since the tool is for A-shares, it is implicit that 'code' is a stock code. A 3 is fair because the parameter is simple and its meaning is highly inferable from the context, but the description still fails to explicitly confirm 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?

States the specific resource (technical indicators for A-shares) and lists the indicators (MA/MACD/KDJ/RSI/BOLL). It does not explicitly name a sibling tool as an alternative, but the context hints that other tools cover different financial aspects. The description is clear enough to distinguish this as the technical-analysis tool.

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

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

The description explicitly tells the agent when to use this tool: when users ask about '技术面/指标/金叉死叉' (technical analysis/indicators/golden cross/death cross). It does not mention when not to use it or name alternatives, but the trigger phrases are strong and specific.

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. The verb '查' (check) implies a read-only operation with no side effects, which is a behavioral trait. However, the description does not explicitly state that it is non-destructive or mention any authentication or rate-limit considerations, though these are likely implicit for a usage 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 a single, short sentence that immediately states the purpose. It is concise, front-loaded, and contains no fluff. Every word contributes meaning. It is appropriately sized for a zero-parameter tool.

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

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

For a zero-parameter tool with an output schema, the description is complete. It tells exactly what the tool does, and there is nothing missing that an agent needs to invoke it correctly. No prerequisites or return details are lacking given the simplicity of the operation 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?

The tool has zero parameters, so the schema is trivially 100% covered. The description adds no parameter-specific information because there are none. Baseline for 0 parameters is 4, and the description does not contradict or detract from that, so a 4 is appropriate.

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

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

The description clearly states the tool's function: checking one's own API usage and remaining quota. It uses a specific verb (查) and a specific resource (API usage), and it is instantly distinguishable from all sibling tools like ashare_bond or ashare_kline, which deal with financial data. There is no ambiguity about what this tool does.

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 its siblings, but the intent is implied: it is the only tool among 22 siblings that deals with API usage rather than market data. No explicit alternatives or exclusions are mentioned, but the context makes it clear this is the dedicated usage-check tool.

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