Server Quality Checklist

Tool Scores

• cancel_orderC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. While it states the action is cancellation and mentions network support, it doesn't describe what happens when an order is canceled (partial fills, fees, confirmation), whether cancellation is immediate or queued, error conditions, or authentication requirements. For a destructive operation with zero annotation coverage, this is insufficient.

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

  Conciseness4/5

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

  The description is extremely concise - a single sentence that communicates the core purpose and network scope. There's no wasted language or redundancy. However, for a destructive operation, some might argue it's too brief given the lack of behavioral details elsewhere.

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

  Completeness2/5

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

  For a destructive operation with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after cancellation, what the response contains, error conditions, or important behavioral constraints. The network scope information is helpful but doesn't compensate for the significant gaps in understanding this tool's behavior.

  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?

  Schema description coverage is 100%, with both parameters clearly documented in the schema. The description adds no additional parameter information beyond what's already in the schema. The baseline score of 3 is appropriate when the schema does all the parameter documentation work.

  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 clearly states the action ('取消指定订单' - cancel specified order) and resource (orders), making the purpose immediately understandable. It adds network scope information ('支持主网和测试网' - supports mainnet and testnet) which provides useful context. However, it doesn't explicitly differentiate from its sibling 'cancel_all_orders' beyond the 'specified' vs 'all' distinction implied in the tool names.

  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. It doesn't mention prerequisites (like needing an open order to cancel), when to use 'cancel_all_orders' instead, or any constraints on which orders can be canceled. The network scope information is helpful but doesn't constitute usage guidance.

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

• get_24hr_tickerC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. While '获取' (get) implies a read operation, the description doesn't disclose important behavioral aspects like rate limits, authentication requirements, whether it returns real-time or cached data, or what happens when no symbol is provided (though the schema covers this).

  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 a single, efficient Chinese sentence that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple data retrieval tool.

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

  Completeness2/5

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

  For a financial data tool with no annotations and no output schema, the description is insufficient. It doesn't explain what statistics are returned (price change percentage, volume, high/low prices, etc.), the data format, or any limitations. The agent would need to guess about the output structure.

  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?

  Schema description coverage is 100% with clear documentation of the symbol parameter. The description adds no additional parameter information beyond what's in the schema. With one parameter and full schema coverage, the baseline of 3 is appropriate.

  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 clearly states the tool's purpose as '获取24小时价格变动统计' (Get 24-hour price change statistics), which is a specific verb+resource combination. However, it doesn't distinguish itself from sibling tools like get_price or get_klines that might provide related price 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 provides no guidance on when to use this tool versus alternatives. With siblings like get_price (current price), get_klines (historical price data), and get_orderbook (market depth), there's no indication of when this specific 24-hour statistics tool is appropriate.

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

• get_klinesC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. '获取' (get) implies a read operation, but the description doesn't disclose rate limits, authentication requirements, data freshness, or what happens when parameters are invalid. For a data retrieval tool with zero annotation coverage, this leaves significant behavioral questions unanswered about performance, reliability, and constraints.

  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 a single, efficient Chinese phrase that directly states the tool's purpose without any wasted words. It's appropriately sized for a straightforward data retrieval tool and gets straight to the point. Every character earns its place in conveying the core function.

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

  Completeness2/5

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

  Given this is a data retrieval tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what K-line data actually returns (open, high, low, close, volume, timestamps), whether results are paginated, time range capabilities, or data source limitations. For a tool that retrieves complex financial time series data, the description should provide more context about the nature and structure of the returned information.

  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?

  Schema description coverage is 100%, with all parameters well-documented in the schema itself (symbol, interval with enum values, limit with default). The description adds no parameter information beyond what's already in the schema - it doesn't explain what K-line data includes, how intervals affect results, or typical use cases for different limit values. The baseline of 3 is appropriate when the schema does all the parameter documentation work.

  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 '获取K线历史数据' (Get K-line historical data) clearly states the verb ('获取' - get) and resource ('K线历史数据' - K-line historical data). It distinguishes this tool from siblings like get_price (current price) or get_orderbook (order book data), but doesn't explicitly mention the distinction. The purpose is specific to retrieving historical candlestick data rather than other market data types.

  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. It doesn't mention when to choose get_klines over get_24hr_ticker (24-hour statistics) or get_price (current price), nor does it specify prerequisites like needing market data access. There's no context about appropriate use cases for historical K-line data versus other market data tools.

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

• get_open_ordersC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. While '获取' (get) implies a read operation, it doesn't specify whether this requires authentication, what data format is returned, whether results are paginated, or if there are rate limits. The description provides minimal behavioral context beyond the basic operation.

  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 a single, efficient Chinese phrase that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple retrieval tool and immediately communicates the core functionality.

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

  Completeness2/5

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

  For a tool with no annotations and no output schema, the description is insufficient. It doesn't explain what 'current pending orders' means operationally, what data structure is returned, or how this differs from related order tools. The agent would need to guess about return format and behavioral characteristics.

  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?

  Schema description coverage is 100%, with the single parameter 'symbol' well-documented in the schema as '特定交易对的挂单，不传则获取所有挂单' (Pending orders for a specific trading pair, if not passed then get all pending orders). The description adds no additional parameter information beyond what the schema already provides, meeting the baseline for high schema 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 '获取当前挂单' (Get current pending orders) clearly states the verb 'get' and resource 'pending orders', making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_order_history' or 'get_orderbook', which also retrieve order-related information.

  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. It doesn't mention how this differs from 'get_order_history' (which likely retrieves completed orders) or 'get_orderbook' (which shows market depth), leaving the agent to infer usage context from tool names alone.

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

• get_orderbookC
  2.9/5.0
  Behavior2/5

  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 but offers minimal information. It doesn't indicate whether this is a read-only operation, if it requires authentication, what rate limits apply, or what format the depth data returns. The description only states what data is retrieved without any operational context.

  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 single Chinese phrase that directly states the tool's purpose. There's zero wasted language or unnecessary elaboration. It's front-loaded with the essential information and doesn't contain any redundant or verbose elements.

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

  Completeness2/5

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

  For a financial data retrieval tool with no annotations and no output schema, the description is insufficient. It doesn't explain what 'depth data' includes (bid/ask levels, quantities, timestamps), whether the data is real-time or delayed, or how to interpret the results. The agent would need to guess about the return format and data characteristics.

  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?

  With 100% schema description coverage, both parameters are well-documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema (symbol as trading pair, limit as depth limit with default 100). This meets the baseline expectation when schema coverage is complete.

  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 '获取订单簿深度数据' clearly states the tool's purpose as retrieving order book depth data. It specifies both the verb ('获取' - get/retrieve) and resource ('订单簿深度数据' - order book depth data), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like get_price or get_klines, which prevents a perfect score.

  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. There's no mention of when to prefer get_orderbook over get_price for price information, or how it differs from get_klines for market data. The agent must infer usage from the tool name alone without any contextual guidance.

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

• get_order_historyC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but offers minimal behavioral context. It doesn't disclose whether this is a read-only operation, what authentication might be required, potential rate limits, pagination behavior (despite the limit parameter), or what format/scope of historical data is returned. The description simply restates the basic purpose without operational details.

  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 single Chinese phrase that directly states the tool's purpose. There's zero wasted language or unnecessary elaboration. While it may be too brief for optimal completeness, it's perfectly structured and front-loaded.

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

  Completeness2/5

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

  For a tool with 2 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what constitutes 'historical' (time range, status filters), doesn't mention the symbol requirement, doesn't describe the return format, and provides no behavioral context. The schema handles parameter documentation, but the description fails to compensate for missing annotation and output information.

  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?

  With 100% schema description coverage, the baseline is 3. The description adds no parameter-specific information beyond what's already documented in the schema (limit with default 500, required symbol parameter for trading pair). No additional context about parameter usage, constraints, or examples is provided.

  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 '获取历史订单记录' (Get historical order records) clearly states the verb '获取' (get) and resource '历史订单记录' (historical order records). It distinguishes from siblings like get_open_orders (current orders) and get_account_info (account data), but doesn't explicitly mention the symbol filtering capability that the schema reveals.

  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?

  No guidance is provided about when to use this tool versus alternatives. The description doesn't mention that this retrieves completed/cancelled orders (vs. get_open_orders for active orders) or that it requires a specific symbol parameter. There's no comparison to other order-related tools like get_klines or get_orderbook.

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

• get_priceC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It only states what the tool does (gets current price) without mentioning any behavioral traits like whether it's a read-only operation, potential rate limits, authentication requirements, error conditions, or what format the price is returned in. This is inadequate for a tool with zero annotation coverage.

  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 single sentence that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple price lookup tool and is front-loaded with the core functionality.

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

  Completeness2/5

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

  Given the lack of annotations and no output schema, the description is incomplete. For a price lookup tool, users need to know what format the price is returned in (decimal, string, with precision), whether it's real-time or delayed, and any authentication or rate limiting considerations. The description provides none of this context, making it inadequate despite the tool's apparent simplicity.

  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 description mentions '指定交易对' (specified trading pair) which aligns with the single 'symbol' parameter. However, with 100% schema description coverage (the schema already fully documents the symbol parameter), the description adds minimal value beyond what's in the schema. It doesn't provide additional context about valid symbol formats or examples beyond what the schema states.

  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 clearly states the tool's purpose as '获取指定交易对的当前价格' (get the current price of a specified trading pair), which is a specific verb+resource combination. It distinguishes from siblings like get_24hr_ticker (which provides 24-hour statistics) or get_orderbook (which provides order book data), though it doesn't explicitly mention these distinctions.

  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. It doesn't mention when to choose get_price over get_24hr_ticker for price data, or when other tools like get_klines might be more appropriate. There's no context about prerequisites or exclusions.

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

• cancel_all_ordersB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. While '取消' (cancel) clearly indicates a destructive write operation, the description lacks critical behavioral details: whether this requires specific permissions, if it's irreversible, what happens on partial failures, rate limits, or response format. The mention of network types adds minimal context beyond the core action.

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

  Conciseness4/5

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

  The description is a single, efficient sentence that front-loads the core functionality. The network support information is relevant but could be more integrated. There's no wasted verbiage, though it could benefit from slightly more structured presentation of key information.

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

  Completeness2/5

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

  For a destructive operation tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what happens after cancellation (confirmation? error handling?), doesn't mention authentication requirements, and provides minimal behavioral context. The sibling tool context suggests this is part of a trading API, but the description doesn't leverage this context adequately.

  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?

  Schema description coverage is 100% with the single parameter 'symbol' well-documented in the schema. The description adds no additional parameter semantics beyond what's already in the schema ('交易对符号' appears in both). With complete schema coverage, the baseline is 3 even without extra parameter information in the description.

  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 clearly states the action ('取消' meaning 'cancel') and target resource ('所有挂单' meaning 'all pending orders') with scope ('指定交易对' meaning 'specified trading pair'). It distinguishes from the sibling 'cancel_order' by specifying it cancels ALL orders rather than individual ones. However, it doesn't explicitly mention the platform context (cryptocurrency exchange) which would make it fully specific.

  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 implies usage context by mentioning '主网和测试网' (mainnet and testnet), suggesting it works on both production and testing environments. However, it provides no explicit guidance on when to use this vs the sibling 'cancel_order' tool, nor does it mention prerequisites like authentication or account status requirements.

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

• place_orderB
  3.1/5.0
  Behavior2/5

  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 mentions that mainnet uses real funds, which is a critical safety warning, but lacks other important details: it doesn't specify authentication requirements, rate limits, whether the order is immediate or queued, what happens on failure, or the response format. For a financial transaction tool with zero annotation coverage, this is a significant gap.

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

  Conciseness4/5

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

  The description is a single, efficient sentence that front-loads the core purpose ('下单交易') and adds a useful contextual note about networks. There's no wasted verbiage, and it's appropriately sized for the tool's complexity. However, it could be slightly more structured by separating the network warning into a distinct clause for clarity.

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

  Completeness2/5

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

  Given the tool's high complexity (financial transactions with real funds), lack of annotations, and no output schema, the description is incomplete. It misses critical behavioral details like authentication, error handling, and response format. The network warning is helpful but insufficient to cover the gaps, making it inadequate for safe and effective use by an AI agent.

  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?

  Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly with descriptions and enums. The description adds no additional parameter semantics beyond what's in the schema (e.g., it doesn't explain price/quantity formats beyond 'string', or clarify symbol conventions). With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but doesn't detract either.

  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 clearly states the tool's purpose as '下单交易' (place order), which is a specific verb+resource combination. It distinguishes this from sibling tools like cancel_order or get_open_orders by indicating it's for creating orders rather than managing or querying them. However, it doesn't explicitly differentiate from all siblings (e.g., it doesn't mention this is for order creation vs. price checking like get_price).

  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 some usage context by mentioning support for mainnet and testnet, with the note that mainnet uses real funds. This implies when to use testnet vs. mainnet. However, it doesn't offer explicit guidance on when to use this tool versus alternatives like market vs. limit orders (though the schema covers this), nor does it mention prerequisites or exclusions relative to siblings.

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

• get_account_infoB
  3.2/5.0
  Behavior2/5

  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 states the tool retrieves account information and balance, implying a read-only operation, but doesn't specify whether this requires authentication, rate limits, data freshness, or potential side effects. For a financial tool with zero annotation coverage, this is a significant gap in transparency.

  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 a single, efficient sentence in Chinese ('获取账户信息和余额') that directly states the tool's purpose with zero waste. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly.

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

  Completeness3/5

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

  Given the tool's complexity (simple read operation with no parameters) and lack of annotations/output schema, the description is minimally adequate. It states what the tool does but omits important context like authentication needs, return format, or error conditions. Without annotations or output schema, the agent lacks guidance on behavioral traits and response structure.

  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 0 parameters, and schema description coverage is 100% (since there are no parameters to describe). The description doesn't need to add parameter semantics, so it meets the baseline of 4 for zero-parameter tools. No additional value is required or provided.

  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 clearly states the tool's purpose as '获取账户信息和余额' (get account information and balance), which is a specific verb+resource combination. It distinguishes this tool from siblings like get_order_history or get_price by focusing on account data rather than market or order data. However, it doesn't explicitly differentiate from all siblings (e.g., get_open_orders also relates to account status).

  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. It doesn't mention prerequisites (e.g., authentication), timing considerations, or comparisons to other tools like get_open_orders for order-related account data. The agent must infer usage from the purpose alone.

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