Server Quality Checklist

Tool Scores

• logoutC
  2.7/5.0
  Behavior2/5

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

  With no annotations, the description must carry the full burden of behavioral disclosure. It only says 'Logout from the trading system' and mentions a return confirmation, but does not disclose side effects, session invalidation, idempotency, or prerequisites. This is insufficient for a state-changing operation.

  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 concise and front-loaded. The 'Args' and 'Returns' sections add minor structure, but the return value is duplicated by the presence of an output schema, making one line slightly redundant. Overall it is efficient.

  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?

  The tool is simple, but the description is incomplete given the ambiguous relationship with 'disconnect'. It fails to explain when to logout, what happens to the session, or how it differs from disconnect, leaving a noticeable gap for an agent.

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

  Parameters2/5

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

  The schema coverage is 0%, and the description merely restates the parameter as 'User account ID' without adding meaningful details like format, purpose beyond identification, or constraints. It does not compensate for the lack of schema descriptions.

  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 (Logout) and the resource (the trading system). While it doesn't explicitly distinguish from sibling 'disconnect', the purpose is specific enough to be understood. It is not a tautology or vague.

  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 on when to use logout versus alternatives like disconnect or login. It only states what the tool does without context on when it should be invoked, making it hard for an agent to choose correctly.

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

• initializeB
  3/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden. It mentions it returns success status and error details, but does not disclose side effects, whether re-initialization resets state, or any required permissions or preconditions. This is insufficient for a state-changing operation.

  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 compact and well-structured with Args/Returns sections, making it easy to scan. It is not verbose, though the Args/Returns format slightly adds structure beyond plain prose, which is appropriate.

  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?

  Despite having an output schema, the description does not provide enough context around when and how to use this tool in the wider workflow. It lacks information about ordering relative to connect/login, prerequisites, or what state changes occur, leaving the agent underinformed for correct invocation.

  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 schema has zero description coverage for the single parameter, but the description compensates by explaining 'trade_das_url' as a 'Trading DAS server endpoint' and providing a concrete example. This adds meaningful semantics beyond the bare schema.

  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 initializes the CTS Trading API with server configuration, naming the specific resource and action. However, it does not explicitly differentiate itself from sibling tools like connect or login, so it stops 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.

  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. It does not mention whether it should be called before connect or login, or any prerequisite ordering. This is a significant gap for a setup operation.

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

• stock_modify_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 does not mention irreversibility, required permissions, side effects on matched/current quantities, or what 'modification result' means. The only behavioral hint is the modify_type parameter, but that is parameter semantics, not tool behavior.

  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 well-structured: a one-sentence purpose, an Args list with one line per parameter, and a Returns line. It is reasonably concise and front-loaded with the key purpose. Some parameter lines are tautological, but the overall length is appropriate for a 16-parameter 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?

  Given the tool's complexity (16 parameters, 8 required), the description lacks critical context: no usage scenarios, no behavioral expectations, no error or success conditions. The Returns line is vague ('Modification result'). While an output schema may exist, the description still fails to provide enough guidance for correct tool selection and invocation without additional context.

  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 0%, so the description must compensate. It lists all 16 parameters and adds minimal meaning for some (e.g., buy_sell: 'Buy (1) or Sell (2)', modify_type: '0=Quantity, 2=Price', new_quantity: '0 to keep unchanged'). However, many entries merely restate the parameter name (e.g., 'condition: Order condition', 'pre_order: Pre-order flag') without providing meaningful semantics, leaving the agent to infer from the schema enums.

  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 opens with a clear, specific verb+resource: 'Modify an existing stock order.' This distinctly differentiates it from sibling tools like stock_new_order, stock_cancel_order, and stock_query_order. The purpose is unambiguous.

  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 on when to use this tool versus alternatives. It does not mention scenarios like changing price or quantity on an open order, nor does it note exclusions (e.g., use stock_cancel_order for full cancellation). The description only states the operation without context.

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

• connectB
  3.2/5.0
  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 disclosing behavioral traits. It only states the action and the return value ('Connection status'), but does not reveal whether the connection is persistent, if it requires prior initialization or authentication, or if it is idempotent. This lack of context could lead to misuse in sequence.

  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 sentences long and every word earns its place. It is front-loaded with the primary action and includes the expected return. No filler or redundant content is present, making it appropriately concise.

  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?

  The description is minimally sufficient for a simple tool with no parameters and an output schema, but it lacks contextual cues about the operation lifecycle. Given the siblings (e.g., 'login', 'disconnect', 'initialize'), it would benefit from clarifying whether 'connect' must be called first or whether it depends on other steps. The description is not fully complete for an agent making sequencing decisions.

  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 no parameters, so there is nothing to explain. Per the baseline rule for 0-parameter tools, this dimension is adequately handled; the description does not need to compensate for missing parameter information.

  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 ('Connect to the trading server') with a specific verb and resource. It distinguishes this tool from siblings like 'disconnect' and 'get_connection_status', though it does not explicitly differentiate from 'login' or 'initialize', which may also involve establishing a connection. Overall, the purpose is easily understood.

  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. The description contains no mention of preconditions, ordering, or exclusions. Sibling tools like 'login', 'initialize', and 'get_connection_status' exist, but no relationships or recommendations are provided.

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

• get_connection_statusB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure. It states that the tool returns connection and authentication status, which is the core behavior, but it does not elaborate on side effects (e.g., whether it's purely a read operation), error conditions, or the structure of the returned status. The behavior is not misleading, but the description is minimal.

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

  Conciseness3/5

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

  The description is very short and front-loaded, which is good. However, the 'Returns:' section is redundant with the first sentence ('Get current connection and authentication status' vs 'Current connection status'), wasting a line. It's concise but could be tighter by removing the duplication.

  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?

  The tool is simple with no parameters and an output schema is present, which reduces the need to describe return values. The description says enough to understand the basic purpose, but it lacks any contextual framing (e.g., when to use in the connection lifecycle relative to connect/login/disconnect). It's minimally complete but not enriched.

  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 takes zero parameters, and the schema trivially covers this (100% coverage). According to the guidelines, a zero-parameter tool gets a baseline of 4, since the description cannot add parameter meaning beyond the empty schema. The description adds no param info, which is fine given there are none.

  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 function: 'Get current connection and authentication status.' This distinguishes it from sibling tools like connect, disconnect, login, and logout by implying a read-only status check. However, it doesn't explicitly name those siblings, so it doesn't fully differentiate why it's not another status-like command.

  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 on when to use this tool versus alternatives. The description only states what it does, not the situations where it's appropriate (e.g., before trading, after connect or login). There are no exclusions or alternative tool references, leaving the agent to infer usage from the name and getter semantics.

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

• stock_new_orderB
  3.2/5.0
  Behavior1/5

  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 only the action and that a confirmation or error message is returned, but does not mention side effects, required authentication/connection state, or whether the order is immediately sent or staged. This is a significant gap for a financial action tool.

  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 well-structured as an Args list, with each parameter on its own line and the one-line purpose at the top. It is appropriately sized for a 12-parameter tool, but it somewhat duplicates schema information (e.g., parameter names and types), which could be trimmed. Still, it is efficient and readable.

  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?

  The description covers parameter meanings and defaults, which is essential given the low schema coverage. However, it lacks higher-level context: it does not mention that a connection/login may be required (given sibling tools like 'connect' and 'login'), does not describe error scenarios, and does not provide an example invocation. The output schema is present but not described, so the return line is the only clue.

  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 schema has 0% description coverage, so the description's parameter list is essential. It adds meaningful detail such as stock symbol format ('2330'), price '0' for market orders, buy/sell values (1/2), date format (YYYYMMDD), and defaults for optional fields. This goes well beyond the schema's bare titles, though some terms like 'CASH' and 'LIMIT' are left unexplained.

  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 opens with 'Place a new stock order,' which clearly specifies the action (place) and the resource (new stock order). This distinguishes it from sibling tools like 'stock_modify_order' and 'stock_cancel_order,' and the intent is immediately clear.

  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 gives no explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or when to prefer a different tool such as 'stock_modify_order' for existing orders. The only hint is the name and the one-line purpose, which implies usage but does not articulate conditions or alternatives.

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

• stock_query_matchB
  3.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses the force_query cache/refresh behavior and the return type ('List of matched trades'), but omits auth requirements, error behavior, and further details about matches.

  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 well-structured with a summary, an Args block, and a Returns line. It is concise, but the Args block largely duplicates schema information, and the Returns line is minimal.

  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?

  For a simple 2-parameter query tool with an output schema, the description provides a basic overview. However, 'matched trades' is vague, and there is no info on pagination, result limits, or edge cases, making it barely sufficient.

  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 0%, so the description must compensate. It adds meaning for force_query ('True to force refresh from server, False to use cache'), but account_id is only restated as 'Account ID', adding no value beyond the schema title.

  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 says 'Query stock trade matches', which is a clear verb+resource combination. It distinguishes from futopt_query_match by specifying 'stock', but doesn't 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?

  No guidance on when to use this tool versus alternatives. It does not reference sibling tools like stock_query_order or futopt_query_match, leaving usage to be inferred entirely from the tool name.

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

• futopt_cancel_orderB
  3.3/5.0
  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 that it returns 'Cancellation confirmation,' which is vague. It does not mention that cancellation is irreversible, what permissions are required, whether it cancels the entire order or a partial quantity, or what happens if the order is already matched. This is a significant gap for a mutating tool.

  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 front-loaded with the purpose, then follows a clean Args/Returns structure. It is appropriately sized for the parameter count and contains no filler. Every line serves a purpose, even if some definitions are weak, making it efficient and easy to scan.

  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 has 11 parameters, no annotations, and an output schema (implied, but return details are not described), the description is incomplete. It does not explain the cancellation semantics (full vs partial), the meaning of 'current_quantity' vs 'quantity', or the structure of the 'Cancellation confirmation.' For a complex financial tool, this leaves too many important questions unanswered.

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

  Parameters2/5

  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 compensate. It lists all 11 parameters but many definitions are tautological (e.g., 'order_number: Order number', 'product_type: Product type'). It does add some value with 'current_quantity: Current remaining quantity' and 'trade_date: Trading date (defaults to today)', but several parameters like 'pre_order: Pre-order flag' remain unclear. The description fails to clarify the relationships between quantity, current_quantity, and matched_quantity, which are crucial for understanding cancellation 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 opens with a specific verb and resource: 'Cancel an existing futures/options order.' This clearly distinguishes the tool from siblings like futopt_new_order, futopt_modify_order, and stock_cancel_order, which operate on different resources or actions. The futures/options qualifier disambiguates from the stock cancel tool.

  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 usage context is implied by the name and the one-line purpose, but there is no explicit guidance on when to use this tool versus alternatives, no prerequisites (e.g., order must exist), and no mention of edge cases like partial cancellation or already-filled orders. A clear 'when to use' statement would have raised this to a 4 or 5.

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

• futopt_query_equityB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full responsibility. It does not disclose whether the tool is read-only, what permissions are needed, or any side effects. The verb 'Query' implies reading, but this is not explicit, and no additional behavioral context is given.

  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-sentence purpose followed by clearly labeled Args and Returns sections. It is brief, well-structured, and contains no unnecessary 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 2-parameter tool with no annotations, the description under-delivers. It lacks usage guidance, behavioral transparency, and contains a contradictory default. While an output schema exists, the description does not reference what 'Account equity details' entails, leaving the return structure unexplained.

  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 adds meaning for trade_date by explaining the empty-string behavior and stating a default, but this conflicts with the schema's default of null. account_id is only described as 'Account ID', adding little beyond the schema. With 0% schema coverage, the description partially compensates but has an inconsistency.

  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 futures/options account equity. This distinguishes it from siblings like futopt_query_order, futopt_query_match, and futopt_query_oi, which focus on orders, matches, and open interest respectively.

  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?

  Usage context is only implied by the resource name and the action 'query'. The description does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or prerequisites. It is adequate but not explicit.

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

• loginB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description is the only behavioral disclosure. It does not mention side effects (e.g., establishing a session), security implications, or reversibility, and only states that it returns a login result.

  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 a clear purpose statement followed by Args and Returns sections. Every sentence is informative and there is no redundant text.

  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?

  For a simple 2-parameter tool with an output schema, the description covers the core purpose and parameters. However, it omits contextual guidance about session behavior and the relationship to 'logout' or 'connect' siblings, leaving some gaps in operational understanding.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate. The Arg descriptions ('User account ID', 'User password') only restate the property names without adding format, constraints, or example values.

  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 'Authenticate user with the trading system' with a specific verb (authenticate) and resource (user/trading system), clearly distinguishing it from siblings like 'connect' and 'get_connection_status'. 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 implies login is a prerequisite for trading activities but does not explicitly state when to use this tool versus 'connect' or 'initialize'. No exclusion criteria or alternative tool references are provided.

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

• stock_cancel_orderB
  3.4/5.0
  Behavior2/5

  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 states the action and that a confirmation is returned, but does not disclose that cancellation is destructive/irreversible, whether the order must be in a specific state, or any authorization requirements. The large parameter list implies validation logic that is not explained.

  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 straightforward list of parameters and a return value, structured for readability. It is longer than typical, but the number of parameters justifies it. The purpose is front-loaded, and each line is concise.

  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?

  Even with an output schema, the description is incomplete for a tool with 15 parameters and many optional fields. It does not explain why all parameters are needed, what the defaults mean, or under what conditions cancellation might fail. The flat parameter list lacks workflow context, which is a significant gap given the tool's complexity.

  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 0%, so the description must compensate. It provides a labeled list of all 15 parameters, adding some meaning like 'current_quantity: Current remaining quantity' and 'trade_date: Trading date (defaults to today).' However, many entries simply restate the parameter name (e.g., 'stock_id: Stock symbol') and it does not explain how the parameters relate to the cancellation process.

  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 'Cancel an existing stock order,' which uses a specific verb and resource. This clearly distinguishes it from sibling tools like stock_new_order, stock_modify_order, and stock_query_order.

  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 the tool is for canceling stock orders, but it does not explicitly state when to use it versus alternatives or mention any prerequisites or exclusions. It does not say 'use this instead of futopt_cancel_order' or note that cancellation is irreversible.

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

• futopt_new_orderA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It mentions placing an order and returning a confirmation, but it does not state that this is a live, likely irreversible trade order, nor does it mention prerequisites like authentication, account validity, or potential failure modes. This is a significant gap for a mutation tool with real-world consequences.

  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 well-structured with a one-sentence purpose followed by an Args list and Returns line. It is appropriately sized for a 13-parameter tool, with no wasted words. The parameter list is readable and front-loaded with the key required fields first.

  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 complexity (13 parameters, zero schema descriptions, no annotations), the description is inadequate for safe and correct use. It lacks critical detail on enum value mappings, behavioral expectations, and prerequisites. The output schema exists, so the return confirmation is sufficient, but the parameter and behavioral gaps make the description incomplete.

  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 lists all 13 parameters with brief explanations, which is essential given the schema has 0% description coverage. However, several explanations are vague or incomplete—for example, 'price_type: Price type (default: LIMIT)' does not enumerate the numeric enum values, and 'pre_order: Pre-order flag' lacks any detail. It provides a baseline but does not fully compensate for the schema's silence.

  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 'Place a new futures or options order.' This uses a specific verb+resource construction that distinguishes it from stock_new_order and the modify/cancel/query siblings. The mention of 'futures or options' directly differentiates it from the stock order tool.

  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 implies usage context by specifying 'new' and limiting to futures/options, which is clear given sibling tools like stock_new_order and modify/cancel/query. However, it does not explicitly state alternatives or when not to use this tool, so it misses the full top-tier guidance.

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

• futopt_modify_orderA
  3.6/5.0
  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. It only states the action and returns a vague 'Modification result.' It does not disclose side effects, prerequisites (e.g., order must be in modifiable state), reversibility, or the meaning of modification types. This is a mutation tool with zero behavioral context.

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

  Conciseness4/5

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

  The description is efficiently structured: a one-sentence purpose followed by a straightforward parameter list and return line. It wastes no words but is a bit terse; still, it earns its place for a parameter-heavy tool.

  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?

  With 15 parameters, 8 required, no annotations, and an output schema that is not shown here, the description is minimally adequate. It provides parameter names and one-liner definitions but omits critical details such as enum meanings, modification type semantics, ordering of operations, or example usage. It is not complete enough for an agent to confidently use the tool without additional knowledge.

  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 description enumerates all 15 parameters with brief human-readable semantics (e.g., 'Original order ID', 'Current remaining quantity', 'Second leg contract ID') that go beyond the schema's bare titles. However, some parameters like modify_type, price_type, and condition lack explanation of their enum values or defaults, so it doesn't fully compensate for the 0% schema coverage.

  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 opens with 'Modify an existing futures/options order,' which is a specific verb+resource statement that clearly differentiates it from sibling tools like futopt_new_order and futopt_cancel_order. The intent is 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?

  Usage is implied by the tool name and purpose ('modify an existing order'), but there is no explicit guidance on when to choose this over alternatives or any exclusions (e.g., cannot modify fully filled orders). It doesn't compare to futopt_cancel_order or futopt_new_order.

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

• futopt_query_matchA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description must disclose behavior. It mentions force_query for refresh vs cache, which is useful, but does not state if the operation is read-only, any side effects, or authentication requirements. Some transparency is present, but incomplete.

  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 concise and front-loaded with the main verb. It includes the Args section and Returns, but could be slightly better structured with formatting. No wasted sentences, though it is minimal.

  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?

  An output schema exists, so return types are covered. However, the description lacks context on what constitutes a 'trade match', how it differs from futopt_query_order, or any preconditions. The cache behavior is useful, but overall completeness is adequate but not comprehensive.

  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?

  Schema coverage is 0%, so the description must compensate. It does explain force_query as 'True to force refresh, False to use cache', adding meaning beyond the schema's title/default. account_id is brief but acceptable. Adequate compensation for the missing schema 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 'Query futures/options trade matches' with a specific verb (query) and resource (futures/options trade matches), distinguishing it from stock_query_match and other sibling tools.

  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 like futopt_query_order or futopt_query_oi. It only mentions the force_query cache behavior, but does not explain under what circumstances to choose this tool.

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

• futopt_query_orderA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description must disclose behavioral traits itself. It does reveal caching behavior through force_query ('True to force refresh, False to use cache'), which is useful. However, it does not explicitly state that this is a read-only operation, or mention potential stale data, pagination, or auth requirements, leaving gaps.

  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 highly concise and well-structured, with a clear one-line purpose followed by Args and Returns sections. Every sentence earns its place, and there is no filler.

  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 that there is an output schema, the return value is already defined. The description covers purpose, parameters, and caching behavior. However, it omits the full product_type enum values (2 and 3) and provides no usage context or prerequisites (e.g., login required). These are minor but notable gaps, making it slightly incomplete.

  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 0%, so the description must compensate. It provides one-line explanations for all three parameters, which adds meaning. However, the product_type mapping is incomplete (only 0 and 1 are listed while the schema enum includes 0-3), and account_id is minimally described as 'Account ID.' It helps but does not fully compensate for schema gaps.

  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 opens with 'Query futures/options orders,' which is a specific verb+resource combination that clearly distinguishes this tool from siblings like futopt_query_match (queries matches) and futopt_new_order (creates orders). The purpose is unambiguous.

  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 explicit guidance on when to use this tool versus alternatives. It does not mention exclusions or alternatives, such as 'for matches, use futopt_query_match.' Usage must be inferred from the name and context, leaving the agent without clear decision support.

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

• set_lot_sizeA
  3.7/5.0
  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. It states the action and gives an example format, but it does not disclose side effects (e.g., whether existing lot sizes are overwritten), permission requirements, reversibility, or error behavior. The return is only vaguely described as 'Operation result,' which adds little 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 compact, using a clear Args/Returns structure. Every sentence is informative: the action sentence, the parameter explanation with example, and the return line. There is no redundant or filler content, achieving excellent conciseness.

  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?

  For a simple one-parameter tool with an output schema, the description covers the main purpose and parameter format adequately. However, it omits preconditions (e.g., requires login/connection) and does not clarify the behavior of the operation beyond the vague 'Operation result.' Since output schema exists, return details are not required, but the missing usage context leaves some gaps.

  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?

  Schema coverage is 0%, so the description must compensate. It provides a concrete example ('0050=1000|0028=1000') that clarifies the expected string format, which is a significant addition beyond the bare schema. However, it does not fully specify the syntax rules (e.g., separators, spaces), so it doesn't earn a 5.

  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: 'Set lot size data for specific stocks.' This uses a specific verb ('Set') and resource ('lot size data') that distinguishes it from sibling tools, which are primarily for orders, queries, and connection management.

  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?

  Usage context is implied rather than explicit: the tool is for configuring lot sizes, and no alternatives are mentioned. There is no guidance on prerequisites such as being logged in or connected, nor any when-not-to-use caveats. This makes it minimally acceptable but lacking clear direction.

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

• stock_query_positionA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It explains the force_query parameter's cache behavior and mentions returns include P&L data, which adds useful context. However, it does not explicitly state whether the operation is read-only or if it requires a connection, leaving some transparency gaps.

  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 concise and well-structured with an Args/Returns format. It avoids fluff and presents all necessary information in a scannable way, though it could be slightly more polished by noting defaults inline.

  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 includes the key return value (positions with P&L data) and parameter semantics, and the output schema exists for detailed return structure. However, it omits any mention of required prerequisites like a valid connection or login status, which are relevant given the sibling tools for connect/login. This is a minor gap.

  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?

  Given the schema has 0% description coverage, the description compensates by explaining each parameter's meaning. It provides the format and default for trade_date, the behavior of force_query (cache vs server refresh), and identifies account_id. While account_id is somewhat redundant, the other parameters gain clarity beyond the schema's basic definitions.

  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 'Query stock positions' with a specific verb and resource, and it distinguishes itself from sibling tools like stock_query_order and stock_query_match by focusing on positions. The purpose is unambiguous and directly tied to the tool name.

  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 on when to use this tool versus alternatives. While the name implies it is for querying positions, there is no explicit context about prerequisites (e.g., being logged in) or exclusions compared to other query tools. The description only states what it does, not when to choose it.

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

• stock_query_orderA
  3.9/5.0
  Behavior3/5

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

  Without annotations, the description discloses the cache-vs-server behavior via the force_query parameter and indicates the return type as a list of current orders. However, it does not explicitly state that this is a read-only operation or mention prerequisites, error conditions, or real-time guarantees.

  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 Args and Returns sections. Every sentence provides necessary information, and there is no unnecessary filler.

  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?

  For a simple query tool, the description covers the essentials: purpose, parameters, and return type. An output schema exists, so not explaining the return structure in detail is acceptable. It could add usage context or prerequisites, but overall it is fairly complete.

  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?

  With 0% schema description coverage, the description fully compensates by explaining account_id as "Account ID" and force_query as "True to force refresh from server, False to use cache". This adds meaningful meaning beyond the schema's types and defaults.

  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 "Query stock orders" with a specific verb and resource, distinguishing it from sibling tools like stock_new_order or futopt_query_order. It makes the tool's scope explicit (stock orders, not futures/options).

  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 given on when to use this tool versus alternatives such as stock_query_match or futopt_query_order. The description only states what it does without contextual hints on when it should be preferred.

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

• disconnectA
  4/5.0
  Behavior3/5

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

  There are no annotations, so the description must carry the behavioral disclosure burden. It only states the action and the fact that a status confirmation is returned. It does not describe side effects, prerequisites, or failure behavior, which for a disconnect operation could be relevant (e.g., pending orders, session state).

  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, with two short sentences that directly state the purpose and the return. Both sentences serve a clear function and there is no filler.

  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 simplicity of the tool (no parameters), an output schema exists, and the description provides the core action and return type, it is mostly complete. It could add a sentence about when it is appropriate to call this tool or how it relates to 'logout', but the current level is adequate for a simple disconnect action.

  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 schema is fully covered. The description does not need to add parameter meaning beyond stating the action, which is sufficient. The baseline of 4 applies because there are no parameters.

  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 action (disconnect) and the target (trading server), making its purpose unambiguous. It distinguishes itself from siblings like 'connect' and 'get_connection_status' by specifying a distinct operation.

  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 when the user wants to end the connection to the trading server, but it does not provide explicit when-to-use guidance or alternatives. It lacks contrast with related tools such as 'logout' or 'connect', so the usage context is only partially implied.

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

• get_accountsA
  4/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the full burden. It discloses the return format ('List of account information objects') and indicates a read-only operation via 'Retrieve'. However, it does not mention authentication requirements, potential errors, or whether a connection must be active.

  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 sentences, directly stating the action and return format without any fluff or redundancy. It is well-structured and front-loaded.

  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?

  For a zero-parameter, read-only list tool with an output schema, the description is sufficiently complete. It could mention prerequisites or relationship to other tools, but that is a minor gap given the simplicity.

  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, and the schema coverage is 100% by default. The baseline for zero parameters is 4, and the description does not need to add parameter information; there is no gap to compensate.

  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 uses the specific verb 'Retrieve' and identifies the resource as 'all available trading accounts', clearly stating the tool's scope. It distinguishes itself from sibling tools, which focus on ordering, querying positions, and connection management.

  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 does not explicitly state when to use this tool vs alternatives or mention prerequisites like login/connection. Usage is implied by the purpose—retrieving accounts—but no exclusions or alternative guidance is provided.

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

• futopt_query_oiA
  4.2/5.0
  Behavior4/5

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

  The description adds behavioral context by explaining the force_query parameter ('True to force refresh, False to use cache') and the trade_date default ('defaults to today'). Since annotations are absent, this information helps the agent understand caching and default 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 a compact docstring with a one-line purpose, followed by parameter explanations and return type. It is front-loaded, free of fluff, and every sentence contributes useful information.

  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 purpose, parameters, and returns. It does not mention prerequisites like login, but the sibling tools suggest connectivity is separate. With an output schema present and parameters well-covered, this is sufficiently complete for a simple query tool.

  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?

  All three parameters are described in plain language, with meaningful interpretation for force_query (refresh vs cache) and trade_date (defaults to today). This adds value beyond the bare schema titles, though it does not detail formats or constraints.

  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 function with a specific verb and resource: 'Query futures/options open interest.' This distinguishes it from sibling tools like futopt_query_order (queries orders) and futopt_query_match (queries matches).

  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 usage is implied by the tool's name and description but no explicit guidance is given about when to choose this over alternatives, nor are any exclusions or prerequisites mentioned. A clear statement like 'use for checking open interest positions' would improve this.

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