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

With no annotations, the description fully discloses behavior: it is a simulated (模擬) operation, computes fees and tax, enforces the 1000-share lot rule, and defines the exact return structure including all fields. It also lists specific error scenarios, providing complete transparency about what can go wrong.

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

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

The description is well-organized into purpose, examples, Args, Returns, and Raises sections. It is comprehensive without being bloated; every sentence adds value, and the critical lot-size rule is highlighted early and repeated in the args section for emphasis.

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

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

For a tool with no output schema and no annotations, the description is complete. It covers input semantics, return fields, error causes, and usage examples. An agent can invoke this tool correctly without needing additional external documentation.

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 has 0% description coverage, so the description must and does compensate. It explains symbol (股票代碼), quantity (must be multiples of 1000), and optional price (defaults to market price), reinforced by concrete examples. Every parameter's meaning and constraints are fully detailed.

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: '模擬台灣股票買入操作' (simulate Taiwan stock buy operation) and details that it executes simulated buy transactions while calculating fees and taxes. It distinguishes itself from sibling tools like sell_taiwan_stock by the buy action, and from get_* tools which are read-only.

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

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

The description provides clear context: it is for simulated buying, with examples showing how to use market and limit orders. It does not explicitly name alternatives or say when not to use it, but the buy vs. sell distinction is obvious from the tool name and sibling list, so the usage context 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 provided, so the description carries the full burden. It discloses the response structure, success/error fields, possible failure reasons, and example outcomes. It does not mention authorization or rate limits, but for a read-only date-checking tool the behavior is described sufficiently.

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

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

The description is well-structured with purpose, examples, arguments, returns, and error conditions. It front-loads the core purpose and each section adds necessary information. Although lengthy, the length is justified because there is no output schema and the return structure must be explained.

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

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

For a one-parameter read-only date check with no annotations and no output schema, the description is essentially complete: it gives the input format, the decision logic, examples, return fields, and error scenarios. The only minor gap is distinguishing it from get_taiwan_holiday_info, which was already reflected in the usage-guidelines score.

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

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

The input schema only declares 'date' as a string with no description, giving 0% schema coverage. The description compensates fully by specifying the YYYY-MM-DD format, providing concrete examples, and explaining the parameter purpose. This is exactly the kind of compensation needed for a single low-information schema 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 checks whether a given date is a Taiwan stock market trading day, with specific conditions (not weekend, not holiday). It is unambiguous and distinct in function from price/order tools, but it does not explicitly differentiate itself from the sibling get_taiwan_holiday_info, so it stops just short of a 5.

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

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

The description gives examples and explains the trading-day condition, making the intended use clear. However, it does not explicitly say when to prefer this tool over alternatives such as get_taiwan_holiday_info, nor does it describe exclusions or edge cases like makeup workdays or rescheduled holidays.

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

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

With no annotations provided, the description carries the full burden and goes beyond a bare summary: it discloses automatic industry-specific report adaptation, the unified MCPToolResponse envelope, the exact data fields, and likely failure causes. This is strong behavioral context, though it stops short of discussing data freshness or external service dependencies.

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 organized with purpose first, then usage examples, parameters, returns, and errors. It is somewhat long, but every section adds information that the schema and annotations do not provide, so the length is justified.

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

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

For a one-parameter read tool with no output schema, the description supplies the return shape, error conditions, and examples, making it largely complete. It lacks only comparative information about when to use the other financial-statement tools and any mention of units/currency, but those are minor given the clear domain 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 0%, so the description must define the symbol parameter; it does so clearly ('公司股票代碼') and reinforces with two real ticker examples. It could add more rules like leading-zero handling, but for a single string parameter the intent is unambiguous.

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 opening sentence '取得上市公司資產負債表' states a specific operation and resource, and the financial-statement type clearly differentiates it from siblings like get_company_income_statement. The industry-adaptation note further clarifies what the returned balance sheet covers.

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 concrete invocation examples but provides no guidance on when to choose this tool over siblings (e.g., get_company_income_statement) or what problem it solves that others don't. Usage context is left entirely to inference.

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 takes on the full burden of behavioral disclosure. It documents the return envelope, nested dividend fields, and common failure modes such as invalid symbols, missing dividend records, and temporary source unavailability. It stops short of specifying currency units, date formats, or explicitly confirming read-only 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 docstring-style organization with Args, Returns, and Raises sections makes the definition easy to parse. Every major section adds value, especially given the absence of annotations and output schema. The opening sentence is slightly redundant with the following explanation, but overall the length is justified.

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 lookup, the description is fairly complete: it covers purpose, expected inputs, return structure, field meanings, and error conditions. The main gaps are explicit sibling differentiation and some formatting/unit details, but an agent can still invoke the tool correctly and interpret its result.

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

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

Schema description coverage is 0%, but the single parameter 'symbol' is clearly defined as a stock code and illustrated with '2330' and '0050'. This is adequate for a one-parameter tool, though it does not specify constraints like numeric-only formats or whether ETF codes are supported beyond the example.

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

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

The description clearly states the tool's action and resource: retrieving a company's dividend distribution history, including cash dividends, stock dividends, ex-dividend dates, and payment dates. It is easily distinguishable from most price/income/financial-statement siblings, though it does not explicitly contrast itself with get_dividend_rights_schedule.

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

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

Usage is implied through the description and concrete examples, such as get_company_dividend("2330"). However, the description does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or edge cases like unsupported symbol formats.

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, and it largely fulfills it. It discloses the industry-detection behavior (自動偵測公司所屬行業並使用相應的財務報表格式), lists supported industry categories, details the complete return structure, and explicitly enumerates likely error reasons. The main gap is that it does not state whether the operation is read-only or if any side effects exist, but for a lookup tool this is minor.

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 longer than average, but every section earns its place: purpose, industry support, examples, parameter spec, return format, and error conditions. It is well-structured with clear headers and code blocks, making it scannable despite the length. A small reduction from 5 because the Returns section could arguably be compressed given the absence of an output schema still justifies its detail.

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 no output schema and no annotations, the description is remarkably complete. It covers what the tool does, how it behaves across industries, the exact return structure with field names, and the possible error scenarios. An agent has everything needed to invoke it correctly and interpret the result 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%, so the description must fully compensate. It does: the Args section clearly defines symbol as '公司股票代碼' with the example '2330', and the usage examples provide concrete values for different industry contexts. With only one parameter, this is complete and actionable 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 begins with a specific verb and resource: '取得上市公司綜合損益表' (obtain listed company income statement), which is unambiguous. It distinguishes itself from siblings like get_company_balance_sheet by naming the exact financial statement type and adding the industry-detection behavior, making the tool's scope immediately clear.

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 through the tool's name and the examples showing common stock symbols, and it explains the industry-specific formatting behavior. However, it does not explicitly state when to prefer this tool over siblings such as get_company_balance_sheet or get_company_profile, nor does it provide exclusion criteria or alternative recommendations. Usage context is clear but not actively differentiated.

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 transparently describes the return envelope (success, data, error, tool), the structure of the nested revenue_data list, and clearly states that failures are returned as error responses with possible causes such as invalid symbol, unpublished data, or source unavailability. This goes beyond minimal expectations, though it does not disclose details like data freshness or pagination.

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

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

The description is well-structured with sections for summary, examples, Args, Returns, and Raises, and important information is front-loaded in the first sentence. While the first two sentences are slightly redundant, every subsequent section provides useful detail without fluff. The overall length is justified by the absence of an output schema.

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

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

Given there is no output schema and no annotations, the description fulfills the full burden by detailing the return value structure (success, data, error, tool), the nested revenue items with their fields, and failure modes. For a simple one-parameter query tool, this is complete enough for an agent to invoke the tool correctly and interpret the response without 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 input schema provides only a bare string parameter 'symbol' with 0% schema description coverage. The description compensates by defining symbol as '公司股票代碼' and giving concrete examples ('2330' for TSMC, '2454' for MediaTek). This gives an agent enough semantic understanding to format the argument correctly, though it could add format constraints such as numeric string length or exchange rules.

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

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

The description clearly states the verb '取得' (get) and the resource '公司月營收資訊' (company monthly revenue information), and expands on the specific data points included (revenue, YoY growth, MoM growth). This distinguishes it from sibling tools like get_company_income_statement or get_stock_monthly_trading by focusing on monthly revenue data rather than broader financial statements or trading statistics.

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

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

The description implies usage is appropriate when querying monthly revenue data of a company, with examples for specific stock symbols. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or conditions, so the guidance remains implied rather than explicit.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains the return envelope structure (success, data, error, tool), the fields within CompanyProfileData, and the possible failure reasons such as delisted symbols or unavailable data sources. Since this is a read-only lookup, the '取得/查詢' verbs and lack of side-effect warnings sufficiently convey behavior, though it stops short of explicitly stating that no data is mutated.

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?

Although the description is somewhat long, it is well-structured into overview, usage examples, Args, Returns, and Raises sections. Every part earns its place because there is no output schema and no annotations to rely on; the format makes it easy to scan and parse.

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

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

For a one-parameter read-only tool with no output schema, the description is complete: it specifies the input format, the expected data fields, the response envelope, and the error conditions. There is no missing information an agent would need to call this tool correctly and interpret its result.

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

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

Schema coverage is 0%, and the schema only says 'symbol' is a required string. The description compensates fully by defining symbol as '公司股票代碼' with '2330' and '2317' examples and showing exactly how to call the function. This adds meaning the schema alone cannot provide.

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

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

The description opens with a specific verb and resource: '取得上市公司基本資訊' (get basic information for a listed company), and then enumerates the exact fields returned, such as company name, industry, chairman, established date, capital, and employees. This clearly distinguishes it from sibling tools that cover income statements, balance sheets, dividends, and other financial-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?

The description provides clear context by explaining that this tool returns company basic profile data and gives concrete usage examples with real Taiwan stock symbols. It does not explicitly state when not to use it or name alternative tools, but the scope is clear enough that an agent can infer it is for basic company information rather than financial statements or trading operations.

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

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

The description discloses error conditions such as nonexistent symbol, no data available, and data source unavailability, plus explains the return envelope structure (success, data, error, tool). With no annotations provided, this meaningful behavioral context helps the agent anticipate failure 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 well-organized with sections for overview, examples, args, returns, and errors. It is somewhat long but every section provides necessary context for an agent to use the tool correctly. The primary functionality is front-loaded in the first sentence.

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 a single optional parameter, no annotations, and no output schema, the description covers the call pattern, the return data fields, and failure scenarios. It does not specify the exact date format or whether the returned data is sorted by date, but these are minor gaps for a schedule-listing tool.

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

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

The input schema only states symbol is a string with default empty. The description adds meaning by explaining its optionality: leaving it empty or omitting it queries all companies, while providing a ticker queries that specific company. Examples with 2330 and 0050 reinforce the expected format. With 0% schema coverage, the description carries the full burden and largely succeeds.

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

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

The description clearly states the tool retrieves a dividend rights schedule (除權息行事曆) and lists the specific information included: ex-dividend dates, record dates, cash/stock dividends, and payment dates. This is distinct from sibling tools like get_company_dividend and get_taiwan_stock_price, 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?

Usage examples show calling with no arguments for all companies or with a symbol for a specific company. It does not explicitly say when to use this instead of get_company_dividend, which appears to be the closest sibling, so it lacks an explicit alternative comparison.

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 clearly explains the data scope (top 10), the response structure, and possible error reasons, which is strong for a read-only ranking tool. It does not explicitly state 'read-only', but the nature of a get operation is clear and it adds meaningful context beyond the schema.

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

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

The description is well-structured with clear sections for Args, Returns, and Raises, and it front-loads the purpose. It is somewhat verbose with the full return field list, but since there is no output schema, this information is necessary and earns its place.

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

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

For a no-parameter query tool with no annotations and no output schema, the description is remarkably complete: it explains the purpose, usage example, return fields, and error conditions. An agent has everything it needs to invoke the tool correctly and interpret the result.

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

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

This tool has zero parameters, and the description explicitly confirms '無參數' along with an invocation example. The baseline for zero parameters is 4, and the description fully compensates by removing any ambiguity about arguments.

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

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

The description clearly states a specific verb ('取得' / get) and resource ('ETF定期定額排名資訊'), and explains that it returns a ranking of regular ETF investment by investor count. It distinguishes itself from sibling tools by naming the exact data type and top-10 scope, so an agent can identify its unique purpose.

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 general use case ('可作為ETF投資參考指標') and a usage example, but it does not explicitly state when to use this tool versus alternatives or when not to use it. The usage context is implied rather than explicitly contrasted with sibling tools.

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

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

No annotations are provided, so the description carries the full burden. It signals a read-style query through '查詢' and '取得' and documents failure modes (non-trading day, source unavailable, service error). It does not explicitly state 'read-only' or side-effect-free, but for a data-retrieval tool the verb choice is sufficiently clear.

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

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

The description is well-structured with clear sections (Examples, Args, Returns, Raises) and is front-loaded with the core purpose. Every section adds information not present in the schema, and the length is justified by the absence of an output schema.

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

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

For a one-parameter tool with no annotations and no output schema, the description covers purpose, parameter semantics, call examples, return structure, and error conditions. Nothing an agent needs to invoke and interpret the result 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?

With 0% schema description coverage, the description fully compensates: it explains the count parameter's meaning, default value (10), and provides three usage examples (count=5, 10, 20). The schema only declares integer and default, so the description is the sole source of semantic content for the parameter.

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

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

The description opens with a clear verb-resource pair ('取得外資持股') and immediately scopes it by industry ('按產業別'), then lists the metrics captured (持股比重, 買賣超). This distinguishes it from sibling get_top_foreign_holdings, which addresses holdings at a different granularity, and makes the tool's purpose unambiguous.

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

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

The description states an explicit use case ('可用於觀察外資對不同產業的偏好與資金流向') and provides multiple parameterized examples showing intended call patterns. However, it does not explicitly mention alternative tools or state when not to use it, so it stops short of full exclusion 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 behavioral transparency burden. It explains the unified response format, enumerates return fields, and lists realistic failure scenarios including non-trading days and temporary service problems. The only gap is ambiguity about how '個股' data is delivered when the tool has no parameters.

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 organized into clear sections: summary, usage example, args, returns, and raises. The usage example is slightly redundant, but the detailed Returns and Raises sections justify the length because there is no output schema.

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

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

For a no-argument read tool, the description covers the key information an agent needs: what data is returned, the structure of the response, and likely failure conditions. The main omission is clarifying whether individual-stock data is returned or how to access it, given the claim about '個股' with zero parameters.

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

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

The input schema has zero parameters and the description explicitly states '無參數', so there is no parameter ambiguity. With zero parameters, the baseline is 4, and the description confirms the absence rather than requiring the agent to infer it from the schema alone.

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 resource ('融資融券資訊') and the scope ('市場整體及個股'), and explains the intended analytical use ('觀察市場籌碼面變化'). This makes it distinguishable from siblings such as price, revenue, or foreign-holdings tools, though it does not explicitly name any sibling.

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

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

The description gives clear context for when to use the tool: when margin trading statistics such as financing balance, short-selling balance, and offset ratio are needed. It does not explicitly mention when not to use it or name alternatives, but the use case is clear enough for an agent to select it appropriately.

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

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

With no annotations provided, the description carries the full burden and does a solid job: it details the exact return structure, error conditions, and source metadata. It also implicitly communicates read-only behavior through the verb '取得'. It stops short of stating frequency, latency, or historical depth, but this is a strong disclosure for a simple read-only 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 well-structured with sections (purpose, index list, usage, args, returns, raises) and the purpose statement is front-loaded. The 10-index list is valuable context, though the usage example more or less repeats the first line, adding slight redundancy.

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

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

Given there is no output schema and no annotations, the description goes far beyond a bare phrase by documenting the full return structure and possible errors. It lacks details on time range or rendering order, but for a no-parameter tool that returns a known set of indices, this is nearly complete.

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

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

The tool has zero parameters, which earns a baseline of 4. The description explicitly confirms 'Args: 無參數' and shows a call with empty parentheses, leaving no ambiguity for an agent.

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

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

The description clearly states the action ('取得' market index data) and the resource ('市場重要指數資料'), and enumerates the 10 specific indices included. However, it does not explicitly differentiate itself from the sibling tool get_market_index_info, such as noting that this returns historical data while the other does 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 provides a basic usage example but gives no guidance on when to use this tool versus alternative market index tools. There is no mention of exclusions or conditions that would route an agent to a sibling tool.

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

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

No annotations are provided, so the description carries the full disclosure burden, and it does substantial work: it details the unified response envelope (success, data, error, tool, metadata), enumerates the exact fields returned, and lists three concrete failure modes (non-trading hours, source unavaidable, missing data). It only omits minor behaviors like possible data latency or cacheing.

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

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

The description is well-organized into clear sections (summary, usage example, args, returns, raises), and the core purpose is front-loaded in the first line. The Returns section is verbose, but that length is justified by the absence of an output schema — it substitutes for structured documentation. Every section earns its place.

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

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

Given zero parameters, no output schema, and no annotations, the description is highly complete: it replaces the missing output schema with a field-by-field return breakdown and documents error conditions. The only noticeable gap is the lack of explicit differentiation from get_market_historical_index, but nothing an agent needs to invoke this tool correctly 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?

With zero parameters, the baseline is 4. The description explicitly states 無參數 (no parameters) and shows the exact invocation syntax get_market_index_info(), so there is zero ambiguity about the call contract. No additional parameter semantics could be expected.

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 (取得/retrieve) and a precisely identified resource (發行量加權股價指數, Taiwan's main stock market index), and clarifies it provides 即時資訊 (real-time information). This sufficiently distinguishes it from the sibling get_market_historical_index, which covers historical data. An agent can confidently select this tool for current weighted-index quotes.

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

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

The description shows a concrete usage example and states it queries real-time index data, which implies appropriate usage. However, it never names alternatives — notably the sibling get_market_historical_index — or states when NOT to use this tool. Explicit routing such as 'for historical index data use get_market_historical_index' would elevate this.

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 explicitly states the 5-minute update interval, potential failure conditions (非交易時段、資料來源暫時無法存取、服務暫時異常), and the complete response structure. This is thorough transparency for a zero-parameter read operation.

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

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

The description is well-organized into Usage, Args, Returns, and Raises sections. The lengthy Returns section is justified because no output schema is present, so all return fields need documentation. The only minor redundancy is rephrasing the purpose in the usage example.

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

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

Despite having no output schema, the description documents all return fields, units, wrapper structure, and error scenarios, making external documentation unnecessary. For a zero-parameter read-only tool, this is comprehensive enough for an agent to invoke it correctly.

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

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

The tool has zero parameters, and the empty input schema already documents this. The description reinforces it with '無參數' and a usage example, adding confirmation without introducing ambiguity. Since there are no parameters to explain, the baseline score of 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 opens with a specific verb and resource: '取得即時交易統計資訊' and enumerates concrete market-wide metrics such as 當盤成交量、成交金額、漲跌家數分布. This clearly distinguishes the tool from sibling tools that focus on individual stocks, historical data, or index quotes.

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

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

The use case is clear from the word '即時' and the note '資料每5分鐘更新一次', implying this tool is for current market-wide trading statistics. It does not explicitly name alternatives or state when not to use it, but the context is unambiguous enough for selection.

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

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

No annotations are provided, so the description bears full responsibility. It thoroughly discloses the return envelope (success, data, error, tool), enumerates the data fields within data, and lists realistic error causes (nonexistent symbol, non-trading day, source unavailable). It does not cover read-only guarantees, authentication, or rate limits, but the return and error behavior is well specified for a GET-style data 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 organized into clear sections (overview, examples, Args, Returns, Raises) with the primary purpose front-loaded. The first two sentences are somewhat redundant ('取得股票日交易統計資訊' vs '提供指定股票當日的詳細交易統計'), but overall the length is justified by the detailed return-field enumeration and error logging.

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 no output schema, the description provides everything an agent needs to invoke it correctly: parameter meaning, example calls, full return structure and field names, and likely failure scenarios. There is no missing critical information.

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

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

The input schema merely defines symbol as a required string with no description (0% coverage). The description compensates fully by defining the parameter as '股票代碼' (stock symbol) and providing two concrete examples ('2330', '0050'). This leaves no ambiguity about what value to supply.

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

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

The description opens with an explicit verb and resource: '取得股票日交易統計資訊' (retrieve stock daily trading statistics). It then details the data covered (成交量, 成交金額, 委買委賣資訊) and gives concrete examples. The '日' (daily) qualifier distinguishes it from sibling tools like get_stock_monthly_trading, get_stock_yearly_trading, and get_real_time_trading_stats.

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

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

Usage is implied through examples and the phrase '當日' (current day), which signals this tool is for daily end-of-day trading statistics. However, the description does not explicitly state when to prefer this tool over alternatives or mention any exclusion conditions, so the agent must infer routing from sibling names and 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?

With no annotations, the description carries the behavioral burden and does a good job: it documents the MCPToolResponse wrapper, nested data fields, and failure reasons. It still doesn't mention data freshness, delivery window, or authentication expectations, but for a read-only data query it is fairly transparent.

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 text is well-organized with sections (purpose, examples, args, returns, raises) and front-loaded. It is a bit repetitive in the opening sentences and longer than necessary in the return list, but the detail is useful since there is no output schema.

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

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

For a one-parameter query with no output schema and no annotations, the description is complete: input semantics, usage examples, full return structure, nested fields, and likely error causes are all present. Nothing essential is missing for correct invocation.

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

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

Schema description coverage is 0%, so the description must explain the lone parameter. It defines symbol as 股票代碼 and gives real examples ('2330', '0050'), fully compensating for 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 states it retrieves/calculates monthly average transaction prices for a stock, which is a specific verb+resource. It is implicitly distinct from monthly trading-volume siblings by focusing on average price, but it does not explicitly name or contrast an alternative sibling.

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

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

It gives explicit use contexts (trend observation, technical analysis, regular-amount investment performance) and a concrete invocation example. It lacks 'when not to use' or explicit alternative routing, so it does not reach 5.

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

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

With no annotations provided, the description carries the full transparency burden. It discloses the unified response envelope, success flag, data structure, and monthly record fields, making the read-only retrieval behavior clear. No hidden side effects or mutations are suggested.

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

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

The description is well-organized with a brief purpose statement, usage examples, and a structured Returns list. It is slightly repetitive by repeating '月交易資訊' in adjacent sentences, but the main purpose is front-loaded and the content earns its place.

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

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

For a simple one-parameter read tool with no output schema and no annotations, the description covers invocation, parameter meaning, return structure, and expected fields. It does not mention sorting order or historical depth of monthly data, but those are not essential for correct invocation.

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

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

The input schema has 0% description coverage, so the description compensates by explaining that symbol is a stock code and by giving two concrete examples ('2330', '0050'). This is sufficient for the single required parameter, though it does not specify formatting constraints or market scope.

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 monthly trading statistics for a stock, including monthly volume, value, average price, and high/low prices. It is specific about the resource and scope, but it does not explicitly differentiate itself from sibling tools such as get_stock_daily_trading or get_stock_yearly_trading.

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

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

The description includes a usage hint ('適合中長期趨勢分析') and concrete invocation examples, implying when the tool is appropriate. However, it does not explicitly state when to prefer this tool over alternatives like get_stock_daily_trading, get_stock_yearly_trading, or get_stock_monthly_average, nor does it provide exclusions.

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

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

With no annotations, the description carries the full burden of behavioral disclosure, and it handles this well: it describes the unified MCPToolResponse envelope, the specific data fields, and the error conditions (invalid symbol, incomplete financial data, temporarily unavailable calculations). It does not mention rate limits or auth, but these are not pressing for a read-only single-parameter retrieval 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 well-structured with a front-loaded purpose, usage examples, Args, Returns, and Raises sections. Although lengthy, every part adds value, especially given there is no output schema or annotations to lean on.

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

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

For a single-parameter tool with no output schema and no annotations, the description is unusually complete: it states exactly what is returned, the shape of the response, the error causes, and how to invoke it. Nothing needed to call the tool correctly 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?

The input schema only declares a string 'symbol' with zero description coverage, so the description must compensate. It fully does: it names the parameter, explains it as a stock code, and provides two concrete usage examples ('2330', '2454') that establish expected format and semantics.

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

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

The description clearly identifies the operation ('取得股票估值比率分析') and specifies the exact resource: valuation ratios (P/E, P/B, dividend yield). It further enumerates the returned metrics, making it unambiguous what the tool does and how it differs from the many sibling tools focused on prices, trading, income statements, or dividends.

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

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

The description implies when to use the tool—when a user needs valuation metrics to assess stock investment value—and provides concrete examples. However, it does not explicitly contrast with sibling tools or state when not to use it, so the routing guidance is implicit rather than explicit.

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

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It clarifies the operation is a read-only query ('查詢'/'取得'), describes the MCPToolResponse envelope and all nested data fields, and lists likely failure causes such as invalid symbol, missing aggregated data, and temporary source unavailability. Minor omissions like rate limits or authentication are not material for this simple query tool.

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

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

The description is well-organized with purpose, examples, Args, Returns, and Raises sections. The detailed return-field breakdown is justified because there is no output schema, so it adds essential value rather than 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 one-parameter read-only tool with no annotations and no output schema, the description provides everything needed to call it correctly: invocation syntax, expected return structure, and error scenarios. Minor details like ordering of yearly data or unit conventions are not critical for successful use.

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

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

The input schema only declares symbol as a required string with 0% description coverage. The description compensates fully by defining symbol as '股票代碼' and providing real examples ('2330' for TSMC, '2454' for MediaTek), so the meaning and format of the parameter are unambiguous.

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

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

The description opens with a specific verb and resource: '取得股票年交易資訊' (get stock yearly trading information). It further enumerates the exact fields returned (yearly volume, amount, average price, yearly change), making it clear that this tool is distinct from sibling tools like get_stock_daily_trading or get_stock_monthly_trading.

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

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

The description clearly states the intended use case: '適合長期投資分析與歷史回顧' (suitable for long-term investment analysis and historical review), and provides concrete calling examples. It does not explicitly mention when not to use this tool or name sibling alternatives, but the annual scope makes the intended 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 discloses the unified return structure (MCPToolResponse with success, data, error, tool), lists the holiday data fields, and explicitly mentions possible error causes such as date format, API service failure, and network issues. This provides meaningful behavioral context beyond the name and covers failure 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 well-organized with clear sections (overview, usage examples, args, returns, raises). The core purpose is front-loaded, and every section adds necessary information without redundancy. It is detailed but not bloated.

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

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

Despite having no output schema and no annotations, the description provides a complete invocation contract: purpose, parameter format, return schema details, error scenarios, and examples. An agent can call the tool correctly and accurately interpret the result with no missing information.

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

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

Schema description coverage is 0% for the only parameter 'date'. The description compensates thoroughly by specifying the exact format YYYY-MM-DD and giving concrete examples like '2025-01-01', '2025-10-06', and '2025-10-07'. An agent knows exactly what to pass without opening 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 states a specific verb '查詢' (query) and a specific resource '台灣節假日資訊' (Taiwan holiday info), and further clarifies the exact function: checking if a date is a national holiday and retrieving its details. It is clearly distinct from the stock-related sibling tools, and the holiday focus separates it from check_taiwan_trading_day even without explicit contrast.

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 three concrete usage examples covering a holiday, a special holiday, and a regular workday, clearly indicating when to use the tool. However, it does not explicitly mention alternatives or exclusions such as 'use check_taiwan_trading_day for trading day queries', so it lacks explicit when-not-to-use guidance.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It thoroughly explains the unified MCPToolResponse format, enumerates all StockPriceData fields, and clearly states error conditions with likely causes. It does not mention potential data latency or rate limits, but for a read-only query tool the behavioral coverage is strong.

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

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

The description is well-structured and front-loaded with the core purpose, followed by symbol formats, examples, args, returns, and errors. It is somewhat long but every section contributes useful information, so no part feels wasted.

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 no annotations and no output schema, the description is complete: it covers input formatting, return structure with field names, and possible error causes. Nothing an agent needs to make a correct call 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 coverage is 0% and the schema only declares symbol as a string. The description fully compensates: it defines symbol as a 4-6 digit code with optional letters or a full/partial company name, gives concrete examples including an ETF, and explains partial-name matching. This adds substantial 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 opens with a clear verb+resource statement: '取得台灣股票即時價格資訊' (get Taiwan stock real-time price info). It further clarifies accepted input types (codes vs. names) with examples, but it does not explicitly distinguish itself from siblings like get_real_time_trading_stats or get_stock_daily_trading.

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

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

Usage is implied through the description of querying by code or company name and the examples provided, but there is no explicit statement of when to use this tool versus alternatives. Sibling tools are not referenced, and no exclusions or conditions are given.

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

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

With no annotations, the description carries the full burden. It discloses failure modes such as non-trading days and temporary service issues, and describes the return envelope. It lacks details like data timing or refresh behavior, but for a read-only no-argument tool the disclosure is reasonably complete.

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

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

The description is well-structured with a summary, usage example, Args, Returns, and Raises sections. There is minor redundancy between the opening sentence and the explanatory second sentence, but overall every major section earns its place.

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

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

For a no-parameter tool with no output schema and no annotations, the description fully covers the return fields, error cases, and invocation. An agent has everything it needs to call the tool and interpret the result.

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

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

The tool has zero parameters, so the input schema is trivially complete and the description's explicit '無參數' plus usage example adds no necessary semantics. The baseline of 4 for zero-parameter tools 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 states a specific verb and resource: it retrieves the top 20 stocks by foreign shareholding percentage, and lists the main returned fields. This clearly distinguishes it from related siblings like get_foreign_investment_by_industry, which covers industry-level foreign investment.

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 use case ('可瞭解外資重點布局標的') and a usage example, making the intended context evident. However, it does not explicitly contrast this tool with alternatives such as get_foreign_investment_by_industry, so some routing inferences are left to the agent.

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

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

With no annotations, the description carries the full burden and discloses simulation semantics, 0.3% transaction tax, the 1000-share lot rule, optional price behavior, failure modes, and the full response structure. This makes the operational behavior predictable and goes well beyond 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 organized into intro, note, examples, Args, Returns, and Raises sections; every section contributes useful information. The 1000-share rule appears in both the note and Args, but this minor redundancy does not hurt 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?

This is a trading action with no output schema, but the description provides input constraints, return fields and their meanings, tax rate, example calls, and error conditions. An agent has everything needed to invoke the tool correctly.

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

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

The input schema has 0% description coverage, so the description must compensate; it fully explains symbol with an example, quantity with the mandatory 1000-multiple constraint, and price as optional/market/default. This adds real meaning beyond the bare schema names and types.

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

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

The description opens with a specific verb and resource: simulating a Taiwan stock sell transaction and computing fees/tax. It also distinguishes the tool from the sibling getters and from buy_taiwan_stock by naming the sell/simulation action.

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

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

Concrete call examples show market and limit orders, and the description states that omitting price means a market order. It also warns about the 1000-share minimum unit. It does not explicitly name alternatives or when-not-to-use, but the sell-vs-buy/getting context is clear.

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