Server Quality Checklist

Tool Scores

• get_tradesA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds useful context by specifying that it returns the most recent trades for the current day ('당일 최근'), but it does not disclose return format, pagination, or other behavioral details. This adds some value beyond the annotations but does not fully elaborate.

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

  Conciseness5/5

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

  The description is brief and well-structured, with a single clear purpose sentence followed by a compact argument list. Every word is useful, and there is no redundancy or fluff.

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

  Completeness4/5

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

  The description, combined with the annotations and output schema, gives a fairly complete picture for a simple read-only tool. It covers purpose and parameters adequately, and the output schema handles return values. The only notable gap is the lack of usage differentiation from sibling tools, but the tool's simplicity makes this a minor omission.

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

  Parameters5/5

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

  The input schema has no descriptions for the parameters, so the Args section in the description is essential. It explains that 'symbol' is the security symbol and 'count' ranges from 1 to 50 with a default of 20, providing meaning beyond the schema's type and default fields. This fully compensates for the 0% schema description coverage.

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

  Purpose4/5

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

  The description states a specific action ('조회한다' - retrieves) and resource ('당일 최근 체결 내역' - today's recent trade executions) for a given symbol. This clearly conveys the tool's function and distinguishes it from siblings like get_orderbook or get_candles, though it does not explicitly name alternatives.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives such as get_orderbook or get_price. It only states what the tool does, with no contextual hints about when it is the appropriate choice, lacking exclusions or prerequisites.

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

• get_orderbookA
  3.8/5.0
  Behavior2/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds no additional behavioral context, such as data latency, order book depth, or exchange-specific behavior, beyond what the annotations already convey.

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

  Conciseness5/5

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

  The description is extremely concise: a one-line purpose statement and a short parameter definition. It is front-loaded and contains no irrelevant or redundant text.

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

  Completeness5/5

  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 an output schema, the description adequately covers the purpose and the required parameter format. Return values are presumably documented in the output schema, so no further explanation is needed.

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

  Parameters5/5

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

  Schema coverage is 0%, so the description must compensate. The Args section explicitly defines the symbol format for KRX (6-digit number) and US (ticker), which is essential additional meaning not present in the schema. This fully addresses the parameter's semantics.

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

  Purpose5/5

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

  The description clearly states that the tool queries bid/ask prices and quantities for a symbol ('종목의 매수/매도 호가와 잔량을 조회한다'). This is a specific verb+resource description that distinguishes it from sibling tools like get_price and get_trades, which focus on different data aspects.

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

  Usage Guidelines2/5

  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 alternatives such as get_price, get_trades, or get_stock_info. It does not mention prerequisites, exclusions, or contextual triggers, leaving the agent without clear selection criteria.

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

• get_price_limitsA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds meaningful behavioral context beyond annotations: the null-return behavior for markets without price limits, and it implies the tool returns both upper and lower limits. This is useful but not exhaustive; for instance, it does not mention error handling or whether the limits are for the current trading day (although '당일' does indicate that).

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

  Conciseness5/5

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

  The description is appropriately concise: one purpose sentence, one behavioral note, and an Args line. It is front-loaded with the core function and contains no redundant or tangential content. Every sentence serves a purpose.

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

  Completeness4/5

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

  Given the tool's simplicity (one parameter, no nested objects) and the presence of an output schema, the description does not need to explain return structure. It covers the main edge case (null for no-limit markets) and clearly defines the input. It is complete for a simple lookup tool, though it could optionally mention how invalid symbols are handled, but that is not essential.

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

  Parameters3/5

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

  The schema has only one parameter, 'symbol', with no description (0% schema description coverage). The description adds '종목 심볼' (stock symbol) in the Args section, which provides basic meaning. However, this is essentially a restatement of the parameter name and does not add nuance like format or examples. It meets the minimum needed to compensate for the schema gap but does not go beyond.

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

  Purpose5/5

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

  The description clearly states the tool's function in Korean: 'retrieves the day's upper/lower price limits for an instrument.' This is a specific verb and resource, and it distinguishes itself from all sibling tools, none of which mention price limits. The action and scope are unambiguous.

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

  Usage Guidelines3/5

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

  The description provides an implicit usage context: use this tool to get price limits. It also adds a relevant behavioral note that null is returned for markets without price limits (e.g., US stocks), which informs when results may be nil. However, it does not explicitly state when to use this tool versus an alternative, nor does it mention any exclusions or prerequisites.

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

• get_candlesA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, and the description aligns with that. The description adds valuable context by explaining pagination via 'before' (pass nextBefore from previous response) and the meaning of 'adjusted' price, which are not obvious from annotations alone.

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

  Conciseness5/5

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

  The description opens with a precise one-sentence purpose, then lists parameters in a clean, bullet-like format. Each parameter description is concise and informative without unnecessary fluff, making it easy to scan.

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

  Completeness4/5

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

  With an output schema present, the description doesn't need to explain return values. It covers all parameters and their interactions (such as pagination), providing enough context to invoke the tool correctly. A minor gap is the lack of explicit mention of OHLCV field names, but the output schema likely covers this.

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

  Parameters5/5

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

  Schema coverage is 0%, so the description carries full responsibility for parameter meaning. It explains all 5 parameters with specific details: interval values ('1m' vs '1d'), count range (1-200, default 30), before semantics (pagination, pass nextBefore), and adjusted flag meaning (default True). This goes well beyond the schema.

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

  Purpose5/5

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

  The description clearly states '종목의 캔들(OHLCV) 차트 데이터를 조회한다' (queries OHLCV chart data for a symbol), using a specific verb and resource. It distinguishes from siblings like get_price (single price) and get_orderbook by specifying candlestick chart data.

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

  Usage Guidelines2/5

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

  The description does not provide any guidance on when to use this tool versus alternatives. It only explains the parameters, with no mention of scenarios that call for candle data or exclusions. There is no explicit instruction on selection.

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

• get_stock_infoA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it is a safe read operation. The description adds useful behavioral context by specifying the exact fields returned (stock name, market, currency, status, shares) and the limit of up to 200 comma-separated symbols, which informs expectations beyond the raw schema and annotations.

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

  Conciseness5/5

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

  The description is concise and well-structured: a clear one-sentence summary followed by a structured Args section. Every word adds value, with no redundancy or filler. It is appropriately sized for a single-parameter read-only tool.

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

  Completeness5/5

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

  Given the tool's simplicity (one parameter, read-only, with an output schema), the description covers the what, the returned fields, and the parameter syntax. Combined with the annotations and output schema, the agent has complete information to select and invoke the tool correctly. The only gap is usage guidance, but that is already scored separately.

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

  Parameters5/5

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

  The input schema provides no description for the 'symbols' parameter, and schema coverage is 0%. The description compensates fully by explaining in the Args section that symbols should be comma-separated and limited to 200, giving both format and constraints. This is essential information beyond the schema's bare type declaration.

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

  Purpose5/5

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

  The description clearly states the tool's purpose with a specific verb ('조회한다' meaning 'retrieves') and a well-defined resource: basic stock information including stock name, listing market, currency, listing status, and number of issued shares. This unambiguous scope distinguishes it from sibling tools like get_price (prices) or get_candles (candlesticks).

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

  Usage Guidelines2/5

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

  The description does not provide any explicit guidance on when to use this tool versus its siblings, such as naming alternatives or stating exclusions. It only describes what the tool does, leaving the agent to infer usage from context. There is no mention of 'use for static reference data' or 'use instead of get_price when you need fundamental data'.

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

• get_stock_warningsA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds the specific set of warning signals the tool inspects, which goes beyond the tool name and gives the agent a concrete understanding of the tool's scope and behavior.

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

  Conciseness5/5

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

  The description is compact: three short sentences plus a structured Args line. It front-loads the main purpose and enumerates the checks without unnecessary filler, making it easy to parse.

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

  Completeness5/5

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

  For a read-only lookup tool with one parameter, an existing output schema, and clear scope, the description covers purpose, warning categories, usage context, and parameter meaning. No critical information is missing.

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

  Parameters3/5

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

  The schema has one parameter 'symbol' with 0% description coverage. The description provides a minimal definition '종목 심볼' (stock symbol), which essentially restates the property name and does not add format, exchange, or usage details. It is adequate but not enriching.

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

  Purpose5/5

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

  The description states '종목의 매수 유의사항을 조회한다' (retrieves purchase cautions for a stock) and explicitly lists the specific warning categories checked (정리매매, 단기과열, 투자경고/위험, VI 발동, 신주인수권). This clear verb+resource+scope strongly distinguishes it from sibling price, orderbook, and trade tools.

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

  Usage Guidelines4/5

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

  The description provides clear usage context: '매수를 검토하는 종목이라면 확인할 가치가 있다' (worth checking if considering buying a stock). It implies when to use the tool, though it does not explicitly name alternatives or exclusions, so it stops short of a 5.

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

• get_rankingsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare read-only and non-destructive behavior. The description adds useful behavioral details: count affects response length, and certain ranking types do not support realtime. It does not, however, mention pagination, rate limits, or sorting order, but these are less critical given the output schema exists.

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

  Conciseness5/5

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

  The description is well-structured: a clear one-line purpose, example queries, then a parameter list. Each parameter explanation is compact and informative without redundancy. It fits the information density needed for a 5-parameter tool.

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

  Completeness4/5

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

  The description covers all parameters, gives usage examples, and notes constraints. However, it does not explicitly state which ranking types are valid for each market_country (e.g., whether TOSS_SECURITIES_TRADING_AMOUNT only applies to KR). This ambiguity is a minor gap given the output schema exists for return structure.

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

  Parameters5/5

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

  The input schema has 0% description coverage, but the description thoroughly documents every parameter: type with all enum values and Korean labels, market_country options, duration allowed values, count range and default, and exclude_investment_caution semantics. This completely compensates for the schema's lack of descriptions.

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

  Purpose5/5

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

  The description clearly states the tool retrieves stock rankings with specific categories (top gainers, losers, trading amount/volume). It also gives example user queries, making the purpose immediately clear and distinct from sibling tools like get_price or get_candles.

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

  Usage Guidelines4/5

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

  The description provides explicit usage context with example queries ('stocks that went up a lot', 'stocks with high volume') and a limitation note (TOP_GAINERS/TOP_LOSERS do not support realtime). It does not explicitly name alternatives, but the sibling tool set makes the distinction clear.

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

• get_exchange_rateA
  4.6/5.0
  Behavior4/5

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

  Beyond the readOnlyHint annotation, the description adds important behavioral context: the rate is updated every minute, is for reference, and may not match actual transaction rates. This helps the agent set expectations, though it does not mention response formats or potential edge cases.

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

  Conciseness5/5

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

  The description is concise and well-structured: a single-sentence purpose, a one-line caveat, and an Args list. Every sentence adds value and the key information is front-loaded.

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

  Completeness5/5

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

  For a simple tool with three optional parameters and an existing output schema, the description covers all necessary aspects: what it does, how to use it, parameter meanings, and a critical limitation. It is complete for selection and invocation.

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

  Parameters5/5

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

  The schema has 0% description coverage, but the description fully compensates. It explains base and quote currencies, their allowed values and defaults, the meaning '1 base = ? quote', and the ISO 8601 format for date_time, along with the behavior when omitted.

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

  Purpose5/5

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

  The description clearly states the tool queries the KRW-USD exchange rate with the verb '조회한다'. It specifies the resource (exchange rate) and the currency pair, distinguishing it from sibling tools that handle stocks, orderbooks, or trades.

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

  Usage Guidelines4/5

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

  The description explains that the rate is a reference display rate updated every minute and may differ from actual transaction rates, implying it is for informational use rather than real transactions. However, it does not explicitly name alternative tools or provide a clear 'when not to use' beyond the caveat.

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

• get_market_calendarA
  4.6/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: returns info for 3 business days (previous, current, next), all times in KST, and empty sessions on closed days. This goes beyond the safety profile but does not describe the exact response structure, though that is covered by the output schema.

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

  Conciseness5/5

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

  The description is concise, with each sentence serving a distinct purpose: purpose, use case, return characteristics, and argument definitions. No redundant or filler content, and it is front-loaded with the main purpose.

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

  Completeness5/5

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

  Given the readOnly annotation, simple parameter set, and existence of an output schema, the description covers all necessary context: input values, timezone, business-day scope, and closed-day behavior. It is fully adequate for an agent to invoke the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description fully compensates by defining both parameters: country accepts 'KR' or 'US', and date is an optional YYYY-MM-DD string. This completely clarifies parameter meaning and formats, addressing the coverage gap.

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

  Purpose5/5

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

  The description clearly states it retrieves market operating hours for KR or US markets and explicitly mentions it is used to check if the market is open. This distinguishes it from sibling tools like get_price or get_candles, which focus on market data rather than market hours.

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

  Usage Guidelines4/5

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

  The description provides a clear use case ('지금 장이 열려 있는지 확인할 때 쓴다' — use when checking if the market is open). However, it does not explicitly mention alternatives or when not to use this tool, so it lacks the 'when-not/alternatives' component for a perfect score.

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

• get_priceA
  4.6/5.0
  Behavior4/5

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

  Beyond the annotations (readOnlyHint, openWorldHint, destructiveHint), the description adds valuable behavioral details: a maximum of 200 symbols per query, that the response includes the stock name, and that include_change triggers an additional daily candle lookup making the request slower. This provides practical context but does not cover error handling or edge cases.

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

  Conciseness5/5

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

  The description is concise and well-structured: it begins with the purpose, then a note about response content, followed by a clear Args section. Every sentence adds value, and the length is appropriate for the information conveyed.

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

  Completeness5/5

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

  Given the tool's low complexity (2 params, 1 required), the presence of an output schema, and annotations that cover safety, the description provides sufficient context for an agent to select and invoke the tool correctly. It covers constraints (200 max), parameter behavior, and performance considerations, making it complete for practical use.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description fully compensates. It explains the symbols parameter with format (comma-separated) and examples ('005930,000660' or 'AAPL'), and details include_change's meaning, its calculation, and performance impact. This goes well beyond the bare schema names.

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

  Purpose5/5

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

  The description clearly states the tool retrieves the current price of a stock, with a specific verb ('조회한다' = retrieves) and resource ('현재가' = current price). It also distinguishes from siblings by noting batch support ('최대 200종목') and implying a focus on current price rather than historical data, which sets it apart from tools like get_candles.

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

  Usage Guidelines4/5

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

  The description gives explicit guidance for the include_change parameter, instructing to enable it only when the user asks about price changes/fluctuations, and warns about performance when many symbols are queried. It also advises verifying the returned stock name when the user mentioned a name. However, it does not explicitly mention alternatives or when not to use the tool, though the context makes this fairly obvious.

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

• refresh_symbolsA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds contextual detail that the action is an immediate cache refresh and that it usually happens automatically, without contradicting the annotations. No side effects or error conditions are mentioned, but the simple nature of the tool makes this acceptable.

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

  Conciseness5/5

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

  The description is two short sentences. The first sentence states the primary action, and the second gives usage context. Every word earns its place, and key information appears immediately.

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

  Completeness5/5

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

  As a zero-argument utility with an output schema, the description fully explains its purpose and when to invoke it. There is no missing information that the agent would need to select or call the tool correctly.

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

  Parameters4/5

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

  The tool has zero parameters, so the baseline is 4. The description correctly avoids adding parameter details since none exist. It adds no parameter-related information, but none is needed.

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

  Purpose5/5

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

  The description clearly states the tool '주식 목록 캐시를 즉시 갱신한다' (immediately refreshes the stock list cache), using a specific verb and resource. This distinguishes it from sibling retrieval tools like get_price and search_symbol, which are data readers.

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

  Usage Guidelines5/5

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

  Explicit guidance is provided: '신규 상장 종목이 검색되지 않을 때 사용한다' (use when newly listed stocks are not found) and '평소에는 자동으로 갱신되므로 부를 필요가 없다' (normally auto-refreshes, so no need to call). This covers both when to use and when not to use.

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

• get_market_indicatorsA
  4.8/5.0
  Behavior4/5

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

  Annotations already indicate read-only and non-destructive, and the description adds that it returns current prices (현재가), conveying point-in-time data. It also documents the exact supported symbol set, a behavioral constraint not present in the schema.

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

  Conciseness5/5

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

  The description is concise and well-structured, with purpose front-loaded in the first sentence, followed by usage guidance and parameter details. No redundant sentences.

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

  Completeness5/5

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

  For a simple one-parameter read-only tool with an output schema and annotations, this description covers purpose, scope, parameter format, and sibling differentiation. It is complete for effective selection and invocation.

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

  Parameters5/5

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

  The schema provides zero description for the 'symbols' parameter, so the description compensates by explaining the comma-separated format and listing all 8 valid symbols. This fully documents parameter usage.

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

  Purpose5/5

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

  The description clearly states it fetches current prices for domestic indices and government bond yields, using the specific verb '조회한다' (fetches). It distinguishes from sibling get_price by explicitly noting individual stock quotes should use that tool.

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

  Usage Guidelines5/5

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

  It provides example queries for KOSPI and bond yields, making when-to-use explicit, and directly states that get_price should be used for individual stock quotes. It also limits scope to the 8 supported symbols, preventing misuse.

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

• search_symbolA
  5/5.0
  Behavior5/5

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

  The description adds behavior beyond the annotations: partial matching, market filtering, default limit, and the disambiguation flow. This gives the agent a clear model of how the tool behaves in various queries, complementing the readOnlyHint and openWorldHint annotations without contradiction.

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

  Conciseness5/5

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

  The description is well-structured and front-loaded with the core purpose. Every section (usage context, examples, disambiguation, args) contributes necessary information without redundancy or fluff.

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

  Completeness5/5

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

  For a symbol lookup tool with an output schema, the description is complete. It covers input semantics, usage guidance, behavioral edge cases, and examples, leaving no obvious gaps for an agent to select and invoke the tool correctly.

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

  Parameters5/5

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

  The schema provides no parameter descriptions, but the description's Args section fully explains each parameter: query supports partial matching, market limits to specific exchanges, and limit has a default of 10. This fully compensates for the schema coverage gap.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: finding stock symbols by name or ticker. It distinguishes itself from sibling tools by explicitly noting that all market price lookup tools require a symbol and this is the first step when a user asks by name.

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

  Usage Guidelines5/5

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

  The description gives explicit instructions on when to use the tool ('사용자가 종목명으로 물으면 먼저 이 도구를 쓴다') and provides concrete examples. It also describes the disambiguation behavior (asking the user when multiple results) which is essential context for interactive use.

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