Server Quality Checklist

Tool Scores

• send_calibrationA
  4.1/5.0
  Behavior2/5

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

  The description only states the action and parameters; it does not disclose potential side effects such as overwriting existing calibration or requiring a connection. With idempotentHint=false, the agent knows the operation is not idempotent, but the description adds no further 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.

  Conciseness5/5

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

  The description is concise, consisting of two sentences. It front-loads the action and then clarifies parameters and purpose, with no redundant 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 the tool's purpose, parameters, and the target system. While it does not mention prerequisites for communication or the exact return behavior, the presence of an output schema mitigates the need for return-value details. Overall, it is adequate for a simple send operation.

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

  Parameters5/5

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

  The description explicitly defines each parameter: x and y as calibration point coordinates in mm, and r as the calibration angle. This provides crucial meaning beyond the input schema, which lists only bare numeric types with no 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 a specific action: sending diffraction calibration parameters to the Hikvision vision host. It also explains the purpose (correcting coordinate mapping), which distinguishes it from sibling tools focused on movement, gripper control, and status checks.

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

  Usage Guidelines4/5

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

  The description provides clear context by stating that the tool is used to correct the coordinate mapping relationship of visual detection. This implies when calibration is needed, though it does not explicitly exclude alternative tools or mention when not to use it.

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

• unlockA
  4.5/5.0
  Behavior4/5

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

  Annotations include only idempotentHint: true. The description adds key behavioral details: it specifically releases the emergency-stop lock, returns an unlock confirmation, and restores normal operation of all motion tools. This goes beyond the annotation and clarifies side effects and post-conditions.

  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 concise sentences, front-loaded with the main action ('解除 emergency_stop 造成的锁定'), and includes essential scope and idempotency information without any filler or redundancy.

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

  Completeness5/5

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

  For a simple parameterless tool with an output schema and idempotency annotation, the description covers purpose, scope, behavior when not locked, and outcome. It is fully self-contained and adequate for an agent to select and invoke correctly.

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

  Parameters4/5

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

  The tool has zero parameters, so the baseline is 4. The description does not add parameter information because there are none; the schema is trivially complete.

  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: '解除 emergency_stop 造成的锁定，恢复运动能力' (unlock the lock caused by emergency_stop, restore motion capability). It uses a specific verb and resource, and explicitly limits scope to emergency-stop locks, distinguishing it from other motion-related 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 Guidelines4/5

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

  The description provides clear usage context: '仅对急停锁定有效' (only effective for emergency stop lock) and '如果未锁定则无操作（幂等）' (no operation if not locked). This implicitly tells when to use and that it is safe to call unconditionally, though it does not explicitly name alternative tools.

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

• get_statusA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and idempotentHint. The description adds that the operation causes no movement and lists the included status fields, reinforcing the safe read-only nature. No conflicting behavior mentioned.

  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?

  Description is two sentences with no filler. Front-loads the core purpose, then adds usage context and alternative in a compact, well-structured manner.

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

  Completeness5/5

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

  Given zero parameters and presence of an output schema, the description covers purpose, usage, and alternative sufficiently. Annotations provide the safety profile, making this contextually complete.

  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 no parameter semantics are needed. The description does not need to explain anything; baseline 4 applies.

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

  Purpose5/5

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

  The description clearly states the tool retrieves a complete robot arm status snapshot including position (X/Y/Z), velocity, motion state, and error code. It distinguishes itself from sibling ping by noting that ping only confirms connection.

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

  Usage Guidelines5/5

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

  Explicitly describes when to use: before movement to confirm starting position, after movement to verify target position, and to calculate available travel. It also names ping as a lighter alternative for connection checks, providing clear when-to-use vs. alternative guidance.

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

• gripper_closeA
  4.7/5.0
  Behavior5/5

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

  Beyond the idempotentHint annotation, the description discloses that the tool returns a confirmation message, is rejected during emergency stop lock, and uses pneumatic control with mutually exclusive M62.0/M62.1 signals, adding substantial 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.

  Conciseness5/5

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

  The description is concise, with a clear front-loaded purpose and relevant details about behavior and safety. No redundant information is present.

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

  Completeness5/5

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

  For a zero-parameter tool with an output schema, the description covers all key aspects: return value, rejection conditions, safety precautions, and control logic. It is sufficient for an agent to invoke it correctly.

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

  Parameters4/5

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

  The tool has zero parameters, and the input schema is empty, so there are no parameter semantics to explain. The description appropriately focuses on behavior rather than parameters, and the baseline for zero-parameter tools is 4.

  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: closing the gripper (夹紧夹爪), with a specific verb and resource. It also distinguishes from the sibling gripper_open by specifying the opposite operation and M62.1 for closing vs M62.0 for opening.

  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?

  It provides a clear safety guideline (confirm the arm has stopped before operating) and notes that it will be rejected during emergency stop lock, which informs when not to use it. However, it does not explicitly name the sibling gripper_open as the alternative, though mutual exclusion with M62.0 is implied.

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

• gripper_openA
  4.7/5.0
  Behavior5/5

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

  The description goes well beyond the idempotentHint annotation by disclosing specific behavioral traits: rejection during emergency stop, the recommendation to stop the arm first, and the pneumatic control mechanism with M62.0/M62.1 and mutual exclusivity. This gives the agent a clear picture of how the tool operates and its 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 concise, front-loaded with the core action ('张开夹爪。返回确认信息'), and each subsequent sentence adds value: rejection condition, pre-operation recommendation, and control details. No wasted words.

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

  Completeness5/5

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

  For a zero-parameter tool with an output schema and idempotentHint annotation, the description covers everything needed: what it does, what it returns, when it fails, and a safety recommendation. It is complete for its 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 input schema has zero parameters, so the baseline of 4 is appropriate. The description adds no parameter-specific details (none are needed), but it does provide contextual information about the control signals that might be relevant to understanding the tool's operation.

  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 using a specific verb and resource: '张开夹爪' (open the gripper) and indicates it returns a confirmation message. This is unambiguous and distinguishes it from the sibling tool gripper_close, which performs the opposite action.

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

  Usage Guidelines4/5

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

  The description provides helpful context about when the tool can and cannot be used, noting that it will be rejected in an emergency stop locked state and recommending that the arm be stopped before operation. However, it does not explicitly contrast with gripper_close or other alternatives, though the purpose is self-evident.

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

• move_jointA
  4.7/5.0
  Behavior4/5

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

  Annotations provide idempotentHint=true, but no readOnly or destructive hints. The description adds useful behavioral context: it affects only joint angles, not Cartesian axes, and returns confirmation of joint ID and target angle. It doesn't discuss error handling or invalid input behavior, but the annotation covers idempotency, and the stated range (0~2) adds safety 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 two sentences, front-loaded with the core action and parameters, and includes a clear usage distinction. Every sentence earns its place with no redundant or fluff content.

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

  Completeness5/5

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

  The tool is simple with only 2 required parameters, and the description covers the purpose, parameter meaning, scope of effect, and alternative tools. An output schema exists, so the return confirmation mention is sufficient. This is complete for an agent to select and invoke the tool correctly.

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

  Parameters4/5

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

  The input schema provides only names and types with 0% description coverage. The description compensates by explaining that joint_id ranges from 0 to 2 and that the angle is specified in degrees. This adds meaning beyond the raw schema, although angle constraints beyond 'degrees' are not detailed.

  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 starts with a specific verb and resource: '控制单个关节旋转到指定角度 (°)' (control a single joint rotation to a specified angle in degrees). It distinguishes itself from siblings by explicitly stating it only affects joint angles, not the Cartesian end-effector axes, and recommends move_to or move_relative for spatial movement.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use this tool (rotating a single joint to an angle) and when not to use it (moving the end-effector to a spatial position). It names the alternative tools move_to and move_relative, providing clear guidance beyond just a general description.

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

• pingA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and idempotentHint; the description reinforces with '无任何副作用' and clarifies the response includes pong and current position. It adds context on output without contradicting annotations.

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

  Conciseness5/5

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

  Description is three sentences, front-loaded with purpose, followed by a safety note and usage guidance. Every sentence contributes value with no redundancy or fluff.

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

  Completeness5/5

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

  For a simple tool with no parameters, an output schema, and safety annotations, the description covers purpose, usage, alternative, and response summary. It is fully sufficient for correct selection and 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 tool has zero parameters (schema has empty properties), so parameter descriptions are unnecessary. The description mentions 'current position' in the return, but no parameter semantics are needed. Baseline 4 for a no-parameter tool.

  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?

  Description uses a specific verb '检查' (check) targeting the resource '机械臂是否在线' (arm online) and states the return values (pong and current position). It clearly distinguishes itself from get_status, which is mentioned as providing full status.

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

  Usage Guidelines5/5

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

  Explicitly states when to use: '用于快速确认连接状态' (for quickly confirming connection status). Gives a direct alternative: '如需完整状态（速度/运动/错误码），用 get_status'.

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

• stopA
  4.7/5.0
  Behavior4/5

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

  The only annotation is idempotentHint=true, which provides little behavioral context. The description compensates by disclosing that power is maintained, stopping is smooth, the arm is not locked, and a confirmation message is returned. This is useful behavioral information, though it could mention additional side effects or safety implications.

  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 front-loaded: the first sentence defines core behavior, the second notes return value, and the third provides usage differentiation. Every sentence adds value without redundancy.

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

  Completeness5/5

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

  The tool is simple with no parameters, and the description covers what it does, the return value, and when to use it compared to emergency_stop. The presence of an output schema covers return details, and no further context seems necessary.

  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?

  With zero parameters, the schema fully defines the input space, and no parameter descriptions are needed. The baseline for zero-param tools is 4, and the description adds no unnecessary parameter details.

  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 performs a decelerated stop ('减速停止'), maintains power, smooth stop, and does not lock the arm. It also explicitly differentiates from emergency_stop by noting lock behavior, making the purpose specific and distinguishing it from siblings.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use this tool ('正常停车用 stop') versus the alternative emergency_stop ('紧急情况下用 emergency_stop'), and explains the key difference (no locking). This gives clear usage guidance.

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

• trigger_visionA
  4.7/5.0
  Behavior4/5

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

  The description goes beyond the idempotentHint annotation by detailing the trigger-to-analysis flow, the output file name, and the recommended polling delay. It could mention error handling or return behavior, but the output schema covers returns, and the timing hint is valuable 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.

  Conciseness5/5

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

  The description is two sentences: the first states the action and effect, the second provides follow-up guidance. Every word earns its place, with no repetition of schema or annotation data.

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

  Completeness5/5

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

  For a zero-parameter trigger tool with an output schema and a simple workflow, the description fully covers the tool's purpose, outcome, timing, and next steps, and references the relevant sibling tools. It is complete and actionable.

  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?

  There are zero parameters, so the schema coverage is trivially 100%. The description adds context about the default 'yanshe' mode, but since no parameters exist, the baseline of 4 applies.

  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 sends a trigger command to the Hikvision vision host for default 'yanshe' diffraction detection, then writes results to a file. This specific verb+resource+mode distinguishes it from sibling tools like send_calibration and read_position_data.

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

  Usage Guidelines5/5

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

  It explicitly instructs to wait 1-2 seconds before calling read_position_data to retrieve results, and directs users to send_calibration for calibration parameters. This provides clear sequencing and alternatives, making when-to-use obvious.

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

• move_relativeA
  4.8/5.0
  Behavior4/5

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

  The description discloses several behavioral traits beyond the idempotentHint=false annotation: it returns target coordinate and speed confirmation, defines coordinate sign conventions, and specifies speed range and default. It does not mention blocking behavior or error handling, but the physical movement context is clear and no contradiction with annotations exists.

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

  Conciseness5/5

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

  The description is concise and well-structured: purpose statement, coordinate legend, usage note, speed default, and alternatives are all presented in a compact, scannable format. Every sentence adds value and the information is front-loaded with the core action.

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

  Completeness5/5

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

  Given the tool's complexity, the sparse schema, and limited annotations, the description is remarkably complete. It covers the operation, units, coordinate semantics, default behavior, return information, and alternatives. The presence of an output schema means the return-value mention is a bonus, not a requirement, and the description still provides it.

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

  Parameters5/5

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

  The input schema has no descriptions and 0% coverage, so the description carries the full burden. It defines the meaning of dx, dy, dz with directional signage, provides speed range [10, 200] and default 100, and gives a practical example. This fully compensates for the schema's lack of parameter explanations.

  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: offset the robot arm end effector relative to its current position in mm. It distinguishes from siblings by explicitly contrasting with move_to (fixed coordinates) and get_status (read-only), and by labeling it the most commonly used movement tool.

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

  Usage Guidelines5/5

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

  The description provides explicit guidance on when to use this tool: for relative moves from the current position. It names alternatives with clear conditions: use move_to for fixed coordinates, use get_status for position queries. The example '用户说「向右 100mm」→ dx=100' makes the intended usage concrete.

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

• move_toA
  4.8/5.0
  Behavior4/5

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

  Annotations only include idempotentHint. The description adds valuable behavioral context: coordinate axes conventions, value ranges for X/Y/Z/speed, default speed (100 mm/s), and that it returns confirmation of target coordinates and speed. However, it does not mention whether the move is synchronous or if there are safety prerequisites, leaving a minor gap.

  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, front-loaded with the primary purpose, then delivers key details in a well-organized sequence (axes, ranges, speed, alternatives). Every sentence adds value with no redundancy.

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

  Completeness5/5

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

  With an output schema present, the description covers input constraints, default behavior, and alternative tools. It is sufficiently complete for safe and effective use of a motion control tool, given the provided annotations and schema.

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

  Parameters5/5

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

  Schema has 0% description coverage, but the description fully compensates by explaining axes directions and ranges for X, Y, Z, and speed, including the speed default. This provides essential meaning for all parameters beyond the schema's basic titles.

  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: '将机械臂末端移动到指定笛卡尔绝对坐标 (mm)' (move the robot arm end-effector to specified Cartesian absolute coordinates). This distinguishes it from siblings by explicitly naming move_relative and get_status as alternatives.

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

  Usage Guidelines5/5

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

  Explicitly provides when to use alternatives: '如果要基于当前位置偏移，用 move_relative。如果只是查询位置，用 get_status（只读）'. This gives clear guidance on tool selection.

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

• read_position_dataA
  4.8/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and idempotentHint annotations, the description adds substantial behavioral context: it always returns the latest timestamped data, explains the file format with multiple objects per line, and describes how data is appended. This enriches the agent's understanding of the tool's runtime 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 well-structured with clear sections for purpose, file format, parameter, return value, and a numbered usage example. Every sentence adds useful information, and the workflow steps make it easy for the agent to follow.

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

  Completeness5/5

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

  Even though an output schema exists, the description explains the return value (color, world coordinates, timestamp) and provides a complete end-to-end usage scenario. It fully covers purpose, input, output, and typical usage, making it self-contained for an agent.

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

  Parameters5/5

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

  The input schema only defines 'color' as a string with a default value, providing no meaning. The description compensates fully by explaining that color is an optional filter with concrete examples ('红色'/'蓝色'/'绿色') and that omitting it returns all objects.

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

  Purpose5/5

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

  The description clearly states it reads a material positioning file from an external vision system and returns objects from the latest scan. It uses a specific verb ('读取') and resource ('物料定位文件'), and distinguishes itself from sibling tools like trigger_vision by focusing on reading data rather than triggering actions.

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

  Usage Guidelines4/5

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

  The description provides a concrete typical usage workflow with move_to, making it clear when to use this tool for grasping operations. However, it does not explicitly mention alternative tools or exclusion criteria, so it stops short of the top score.

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

• emergency_stopA
  4.9/5.0
  Behavior5/5

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

  Beyond the annotations (destructiveHint, idempotentHint), the description discloses irreversible locking ('不可逆地锁定机械臂'), that all motion commands are rejected until unlock, and that a confirmation is returned. It also explicitly references destructiveHint=true, confirming consistency with annotations while adding recovery 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 compact and front-loaded: first sentence states the action and return, second explains the irreversible lock and recovery, third provides usage triggers and sibling contrast. Every sentence earns its place with no redundancy.

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

  Completeness5/5

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

  Given no parameters and an existing output schema, the description covers the tool's purpose, when to use it, its destructive/locking behavior, how to recover via unlock, and the sibling distinction. It is fully complete for an agent to select and invoke the tool correctly.

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

  Parameters4/5

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

  There are zero parameters, so the schema fully covers them. The description adds no parameter-specific semantics, but the baseline of 4 for zero-parameter tools applies because no additional parameter explanation is needed.

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

  Purpose5/5

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

  The description states a specific verb+resource: '立即切断动力并锁定所有运动' (immediately cut power and lock all motion), and explicitly distinguishes it from the sibling tool 'stop' by noting 'stop 只是减速，不锁定' (stop only decelerates, does not lock). This clearly defines the tool's unique purpose.

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

  Usage Guidelines5/5

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

  It provides explicit when-to-use guidance: '用户说「停下!」「急停!」「STOP!」时应使用此工具' (use this tool when the user says stop/emergency stop), and contrasts with the alternative 'stop' by explaining that stop does not lock and allows immediate movement. It also mentions the unlock requirement, giving the agent a clear decision path.

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

• homeA
  4.9/5.0
  Behavior5/5

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

  The description adds behavioral context beyond the idempotentHint annotation: it explains the instantaneous nature, simulation mode, the automatic move to Y=-180, and that no unlock is needed. This gives the agent critical operational knowledge.

  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 sentences, front-loading the main action and then providing usage guidance. Every sentence adds value with no wasted words.

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

  Completeness5/5

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

  For a zero-parameter tool with an output schema present, the description is complete. It covers the full behavior, includes important caveats (simulation mode, no unlock), and directs users to alternatives, making it self-sufficient.

  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 the schema provides full coverage. The description does not need to explain parameters; baseline for zero parameters is 4, and the description appropriately does not add redundant parameter information.

  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: all axes return to origin (0,0,0) and then move to Y=-180 safe position. It uses specific verbs and resources, distinguishing it from sibling tools like stop and emergency_stop.

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

  Usage Guidelines5/5

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

  Explicit guidance is provided: homing is instantaneous in simulation mode, does not require unlock (unlike emergency stop), and users are directed to use stop for smooth deceleration without homing. This clearly indicates when to use this tool versus alternatives.

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