Server Quality Checklist

Tool Scores

• generateContextPromptB
  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 states the tool generates a text prompt, but doesn't describe behavioral traits like whether it's read-only or mutating (though 'generate' suggests creation), what format the prompt takes, whether it has side effects, or any performance considerations. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.

  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 in three sentences: first states the purpose, second explains usage context, third lists content components. Each sentence adds value without redundancy. It could be slightly more front-loaded by emphasizing the core action earlier, but overall it's efficient.

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

  Completeness3/5

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

  Given the tool has 0 parameters (simple complexity) and no output schema, the description is moderately complete. It covers the purpose and output content but lacks details on behavioral traits (e.g., side effects, format) and usage guidelines relative to siblings. For a tool in a server with many plan-related siblings, more contextual differentiation would improve completeness.

  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 0 parameters with 100% schema description coverage, so no parameters need documentation. The description doesn't mention any parameters, which is appropriate. It adds value by explaining the output's purpose and content (e.g., includes overall goals, current tasks, executable task lists), compensating for the lack of output 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's purpose: '生成一个详细的文本提示，总结计划的当前状态' (generate a detailed text prompt summarizing the current state of the plan). It specifies the verb '生成' (generate) and resource '文本提示' (text prompt), and mentions the content includes overall goals, current tasks, and executable task lists. However, it doesn't explicitly differentiate from siblings like 'dumpPlan' or 'getPlanStatus' which might provide similar plan state information.

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

  Usage Guidelines2/5

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

  The description provides minimal usage guidance: '这个提示可以作为上下文提供给AI模型，以帮助其决定下一步行动' (this prompt can be provided as context to an AI model to help it decide next actions). It implies usage when AI needs context for decision-making, but offers no explicit when-to-use vs. when-not-to-use rules, no prerequisites, and no alternatives among the many sibling tools (e.g., vs. 'dumpPlan' or 'getPlanStatus').

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

• getExecutableTaskListB
  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. While it describes what the tool returns (a list of executable pending tasks), it doesn't address important behavioral aspects like whether this is a read-only operation, potential side effects, authentication requirements, rate limits, or error conditions. The description is minimal and lacks the depth needed for a mutation-free tool with zero annotation coverage.

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

  Conciseness4/5

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

  The description is appropriately concise with two sentences: one stating the purpose and one describing the return type. Both sentences earn their place by providing essential information. It's front-loaded with the core functionality. Minor improvement could be made by integrating the return information more seamlessly, but overall it's efficient.

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

  Completeness3/5

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

  Given the tool has zero parameters, no annotations, and no output schema, the description provides adequate basic information about what the tool does and what it returns. However, it lacks important context about behavioral traits (safety, side effects) and doesn't help differentiate from sibling tools in a crowded task management domain. The description meets minimum requirements but leaves gaps in usage guidance and behavioral transparency.

  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 schema description coverage is 100% (empty schema). The description appropriately doesn't waste space discussing non-existent parameters. It focuses on the tool's purpose and return value, which is the correct approach for a parameterless tool. A perfect score isn't given because the description could theoretically mention why there are no parameters, but this is minor.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '获取当前所有依赖已满足且状态为 'pending' 的可执行任务列表' (Get a list of all currently executable tasks with dependencies satisfied and status 'pending'). It specifies the verb ('获取' - get) and resource ('可执行任务列表' - executable task list) with filtering criteria. However, it doesn't explicitly differentiate from sibling tools like 'getTaskList' or 'getCurrentTask', which prevents a perfect score.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. There are multiple sibling tools related to tasks (getTaskList, getCurrentTask, getPlanStatus) with overlapping domains, but the description doesn't indicate when this specific filtered list is appropriate versus other task retrieval tools. No exclusions or prerequisites are mentioned.

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

• getTaskListB
  3.1/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool returns a list of tasks and allows optional status filtering, but lacks details on permissions, rate limits, pagination, or error handling. For a read operation with no annotation coverage, this leaves significant gaps in understanding its 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 and concise, with a clear purpose statement followed by Args and Returns sections. Each sentence adds value: the first states the core function, the second explains filtering, and the parameter/return details are necessary. It could be slightly more front-loaded by integrating the filtering note into the first sentence.

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

  Completeness3/5

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

  Given the tool's low complexity (1 optional parameter) and lack of annotations/output schema, the description is minimally adequate. It covers the basic purpose and parameter semantics but misses behavioral aspects like response format details or usage context. For a simple read tool, this is acceptable 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?

  The description adds meaningful semantics beyond the input schema. The schema only indicates an optional 'status_filter' string with no description, but the description explains it's for filtering tasks by status and lists acceptable values ('pending', 'in_progress', etc.). This compensates for the 0% schema description coverage, though it doesn't detail default behavior when null.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '获取计划中所有任务的列表' (get a list of all tasks in the plan). It specifies the verb ('获取列表') and resource ('计划中所有任务'), making the function unambiguous. However, it doesn't explicitly differentiate from siblings like 'getCurrentTask' or 'getExecutableTaskList', which reduces it from a perfect score.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It mentions filtering by status but doesn't compare to siblings like 'getCurrentTask' (for a single task) or 'getExecutableTaskList' (for executable tasks). Without this context, an agent might struggle to choose between similar list-retrieval tools.

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

• getPlanStatusB
  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 behavioral disclosure. While it indicates this is a read operation (获取 - get/retrieve), it doesn't specify whether this requires authentication, has rate limits, returns real-time vs cached data, or what happens if no plan exists. For a tool that presumably accesses plan data, this leaves significant behavioral questions unanswered.

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

  Conciseness5/5

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

  The description is a single, efficient sentence that immediately states the tool's purpose and scope. Every word contributes meaning - '整个计划' (entire plan), '全面概览' (comprehensive overview), and the specific elements returned. There's no redundancy or unnecessary elaboration.

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

  Completeness3/5

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

  Given the tool has no parameters and no output schema, the description provides adequate basic information about what the tool returns (metadata, progress, task status statistics). However, without annotations or output schema, it doesn't specify the format, structure, or completeness of the returned data. For a status retrieval tool among many plan-related siblings, more context about the return value would be helpful.

  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 coverage 100%), so the description appropriately doesn't discuss parameters. The baseline for zero-parameter tools is 4, as there's no parameter documentation burden. The description focuses correctly on what the tool returns rather than what it accepts.

  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 what the tool does ('获取整个计划的全面概览' - get a comprehensive overview of the entire plan) and specifies the scope of information returned (metadata, progress, task status statistics). It distinguishes this from sibling tools like getTaskList or getCurrentTask by focusing on overall plan status rather than individual tasks. However, it doesn't explicitly contrast with dumpPlan which might also provide plan information.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. With siblings like getTaskList, getCurrentTask, dumpPlan, and visualizeDependencies that all provide different aspects of plan information, there's no indication of when this comprehensive overview is most appropriate versus more focused tools. No prerequisites, timing considerations, or exclusion criteria are mentioned.

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

• failTaskB
  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 full burden for behavioral disclosure. It states the tool marks tasks as failed but doesn't describe what 'failed' means in the system context, whether this action is reversible, what permissions are required, or what happens to dependent tasks. For a mutation tool with zero annotation coverage, this is insufficient 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 well-structured with a clear purpose statement followed by parameter explanations. Each sentence adds value, though the formatting with 'Args:' heading could be more integrated. It's appropriately sized for a 3-parameter tool without unnecessary verbiage.

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

  Completeness3/5

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

  Given 3 parameters with 0% schema coverage and no annotations or output schema, the description does well on parameters but lacks behavioral context. For a mutation tool that changes task state, the description should explain more about system behavior, consequences, and typical usage patterns to be truly 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?

  The description provides excellent parameter semantics beyond the 0% schema coverage. It explains task_id is '从0开始' (starting from 0), error_message describes the failure reason, and should_retry is optional with default True. This fully compensates for the lack of schema descriptions and adds meaningful context about parameter usage.

  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 verb ('标记为' - mark as) and resource ('任务' - task) with the specific state 'failed'. It distinguishes from siblings like completeTask and skipTask by specifying the failure state. However, it doesn't explicitly contrast with all sibling tools like dumpPlan or visualizeDependencies, keeping it at 4 rather than 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?

  The description provides no guidance on when to use this tool versus alternatives like skipTask or completeTask. It mentions the tool's function but offers no context about appropriate use cases, prerequisites, or exclusions. This leaves the agent without clear decision-making criteria.

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

• visualizeDependenciesB
  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 full burden for behavioral disclosure. It describes what the tool does (generates visualization) and the return type (string), but doesn't address important behavioral aspects: whether this is a read-only operation, what '当前任务' (current task) refers to in context, whether it requires specific state or permissions, or any performance characteristics. The description is functional but lacks behavioral context needed for safe invocation.

  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 and appropriately sized. It leads with the core purpose, then provides clear parameter documentation in an 'Args' section, and concludes with return information. Every sentence earns its place, though the Chinese-to-English code values might create minor cognitive friction for English-speaking agents.

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

  Completeness3/5

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

  Given the tool's moderate complexity (visualization generation with format options), no annotations, and no output schema, the description is minimally adequate. It covers the purpose and parameters well, but lacks context about what 'current task dependencies' means, how the visualization is structured, or any limitations. The absence of behavioral context and sibling tool differentiation leaves gaps for an agent trying to use this effectively.

  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 adds significant value beyond the input schema. With 0% schema description coverage and only one parameter, the description fully documents the 'format' parameter: it explains the optional nature, acceptable values ('mermaid', 'tree', 'ascii'), what each format produces, and the default value ('ascii'). This completely compensates for the lack of schema documentation.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '生成当前任务依赖关系的可视化图' (generate a visualization of current task dependencies). It specifies the verb ('生成' - generate) and resource ('当前任务依赖关系的可视化图' - visualization of current task dependencies). However, it doesn't explicitly distinguish this from sibling tools like 'dumpPlan' or 'getTaskList' which might also provide task information in different formats.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'dumpPlan' (which might output plan data), 'getTaskList' (which might list tasks), or 'editDependencies' (which modifies dependencies). There's no context about when visualization is preferred over other representations of task dependencies.

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

• getCurrentTaskA
  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 of behavioral disclosure. It states the tool returns task details for 'in_progress' tasks, but does not describe what happens if no such task exists (e.g., returns null, error, or empty), any rate limits, authentication needs, or side effects. For a tool with zero annotation coverage, this leaves significant gaps in understanding its 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 appropriately sized and front-loaded: the first sentence clearly states the purpose, and the second specifies the return type. There is no wasted text, though the structure could be slightly improved by integrating the return information more seamlessly. Overall, it is efficient and earns its place.

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

  Completeness3/5

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

  Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is adequate but not fully complete. It explains what the tool does and the return type, but lacks details on edge cases (e.g., no in_progress task) and behavioral traits. For a basic read operation, it meets minimum viability but could benefit from more context.

  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 0 parameters with 100% coverage, so the schema fully documents the lack of inputs. The description does not add parameter-specific information, which is unnecessary here. Baseline is 4 for 0 parameters, as no additional semantic clarification is needed beyond the schema's completeness.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: '获取当前标记为 'in_progress' (正在进行中) 的任务详情' (Get details of the task currently marked as 'in_progress'). It specifies the exact verb ('获取' - get) and resource ('任务详情' - task details) with a precise scope filter ('in_progress'), and distinguishes it from siblings like getTaskList (which returns all tasks) or getExecutableTaskList (which returns executable tasks).

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

  Usage Guidelines3/5

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

  The description implies usage context by specifying 'in_progress' tasks, suggesting it should be used when the agent needs details about the currently active task. However, it does not explicitly state when to use this tool versus alternatives like getTaskList or getPlanStatus, nor does it provide exclusions or prerequisites. The guidance is functional but not comprehensive.

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

• addTaskA
  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 full burden but lacks critical behavioral details. It doesn't disclose whether this operation is idempotent, what happens if dependencies don't exist, if there are rate limits, or what authentication/permissions are required. The description covers basic functionality but misses important behavioral traits for a mutation 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 with a clear opening sentence followed by organized Args and Returns sections. While efficient, the Returns section could be more concise since there's no output schema, but overall it's appropriately sized with minimal waste.

  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 mutation tool with no annotations and no output schema, the description provides adequate parameter semantics but lacks behavioral context. It covers what the tool does and parameter meanings, but doesn't address error conditions, side effects, or return format details. Given the complexity of task management, more behavioral transparency would be beneficial.

  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 providing clear semantic explanations for all 4 parameters. It explains name uniqueness, dependency format (list of task IDs starting from 0), reasoning purpose, and the optional positioning parameter with default behavior. This adds substantial value beyond the bare schema.

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

  Purpose5/5

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

  The description clearly states the verb ('add') and resource ('new task') with specific context ('to current plan'). It distinguishes from siblings like 'editDependencies' or 'completeTask' by focusing on creation rather than modification or completion.

  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 needing to add a task to the current plan, but doesn't explicitly state when to use this vs alternatives like 'initializePlan' (for starting) or 'editDependencies' (for modifying). It mentions the optional 'after_task_id' parameter for positioning, which provides some contextual guidance.

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

• initializePlanA
  4.1/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. While it mentions the tool can '初始化或完全替换' (initialize or completely replace), it doesn't disclose critical behavioral traits: whether this overwrites existing plans, what permissions are needed, whether the operation is reversible, what happens to incomplete tasks in replaced plans, or what the response looks like. For a mutation tool with zero annotation coverage, this is inadequate.

  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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by structured parameter explanations. Every sentence earns its place by clarifying parameter usage. Minor improvement could be integrating the parameter details more seamlessly, but it's highly efficient.

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

  Completeness3/5

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

  Given the tool's complexity (creating/replacing entire plans with nested task structures), no annotations, and no output schema, the description is partially complete. It covers purpose, usage, and parameters well, but lacks behavioral details (e.g., mutation effects, error conditions, return values). For a tool with this scope, more context about the operation's impact would be beneficial.

  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 providing detailed parameter semantics. It explains that 'goal' describes the plan's overall objective, and 'tasks' is a list where each task has a unique name, dependencies (as names or IDs), and reasoning explaining why the task is needed. This adds essential meaning beyond the bare schema.

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

  Purpose5/5

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

  The description clearly states the tool's purpose with specific verbs ('初始化或完全替换') and resource ('任务计划'), distinguishing it from siblings like 'loadPlan' (which presumably loads existing plans) and 'addTask' (which adds to existing plans). It explicitly indicates this tool creates or replaces entire plans, not incremental modifications.

  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 usage guidance by stating this tool is for '初始化或完全替换一个新的任务计划' (initialize or completely replace a new task plan), which clearly distinguishes when to use this versus alternatives like 'addTask' (for incremental additions), 'loadPlan' (for loading existing plans), or 'editDependencies' (for modifying dependencies in existing plans). The scope is well-defined.

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

• loadPlanA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it '直接覆盖内存中的整个计划' (directly overwrites the entire plan in memory), which is a destructive operation, and warns to use it cautiously. This covers the mutation aspect and potential impact, though it doesn't detail error handling, permissions, or response format.

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

  Conciseness5/5

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

  The description is appropriately sized and front-loaded: the first sentence states the purpose, the second warns of risks, and the Args section clearly explains the parameter. Every sentence adds value without redundancy, making it efficient and well-structured for quick understanding.

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

  Completeness4/5

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

  Given the tool's complexity (destructive operation with one nested parameter) and no annotations or output schema, the description is mostly complete. It covers purpose, behavior, and parameter details. However, it lacks information on return values or error cases, which could be useful given the mutation nature, though not strictly required without an output 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?

  The schema description coverage is 0%, so the description must compensate. It adds significant meaning beyond the schema: it specifies that 'plan_data' is a dict with three top-level keys ('meta', 'state', 'tasks') and notes it's typically exported by 'dumpPlan'. This fully documents the parameter's structure and usage context, compensating 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 tool's purpose: '通过一个完整的计划对象加载或替换当前计划' (load or replace the current plan with a complete plan object). It specifies the verb ('加载或替换' - load or replace) and resource ('当前计划' - current plan). However, it doesn't explicitly differentiate from siblings like 'initializePlan' which might also set up a plan, though 'dumpPlan' is mentioned as a source for the data.

  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 by mentioning that plan data '通常由 dumpPlan 工具导出' (usually exported by the dumpPlan tool), which suggests a workflow. It also warns '请谨慎使用' (use with caution) due to overwriting. However, it doesn't explicitly state when to use this versus alternatives like 'initializePlan' or provide clear exclusions, leaving some ambiguity.

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

• completeTaskA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses the mutation behavior (marking as completed) and the downstream effect (unlocking dependencies), which are valuable. However, it doesn't mention permission requirements, whether the action is reversible, error conditions, or what happens if the task is already completed.

  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 efficiently structured with two sentences: first states the core action and its importance, second provides parameter semantics. Every sentence adds value with zero wasted words, and key information is front-loaded.

  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 mutation tool with 2 parameters, 0% schema coverage, no annotations, and no output schema, the description does a decent job explaining the action and parameters. However, it lacks details about return values, error handling, and behavioral nuances like idempotency or side effects, leaving some gaps in completeness.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must fully compensate. It provides clear semantic meaning for both parameters: 'task_id' is explained as '需要标记为完成的任务的ID (从0开始)' (ID of task to mark as completed, starting from 0), and 'result' as '描述任务完成结果或产出的字符串' (string describing task completion result or output). This adds essential context beyond the bare schema.

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

  Purpose5/5

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

  The description clearly states the verb ('标记为 completed' - mark as completed) and resource ('指定ID的任务' - task with specified ID). It distinguishes from siblings like 'failTask' (marks as failed) and 'skipTask' (bypasses task), establishing a specific completion 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 clear context by stating this is '关键步骤' (key step) for unlocking dependent tasks, which implies it should be used when a task is successfully finished. However, it doesn't explicitly mention when NOT to use it or name alternatives like 'failTask' for unsuccessful outcomes.

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

• dumpPlanA
  4.2/5.0
  Behavior3/5

  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 describes the core functionality (exporting complete plan data as a dictionary) and mentions the output can be used by loadPlan for state restoration, which adds useful context. However, it doesn't disclose potential side effects, performance characteristics, or detailed behavioral traits beyond the basic operation.

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

  Conciseness5/5

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

  The description is perfectly concise with two focused sentences: the first explains what the tool does and its relationship to loadPlan, the second describes the return value. Every sentence earns its place, and the information is front-loaded with the core purpose stated immediately.

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

  Completeness4/5

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

  Given the tool's simplicity (0 parameters, no annotations, no output schema), the description provides adequate context by explaining the export functionality, the dictionary format output, and the relationship with loadPlan. For a simple data export tool, this is reasonably complete, though it could potentially mention performance considerations for large plans.

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

  Parameters4/5

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

  The tool has 0 parameters with 100% schema description coverage, so the baseline would be 4 even without parameter information in the description. The description appropriately doesn't discuss parameters since none exist, and instead focuses on the tool's purpose and output semantics.

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

  Purpose5/5

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

  The description clearly states the specific action ('导出' meaning 'export') and resource ('当前完整的计划数据' meaning 'current complete plan data'), and distinguishes it from sibling tools by mentioning its complementary relationship with loadPlan for state restoration. It provides a precise verb+resource combination that differentiates it from other plan-related 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 explicitly states when to use this tool ('导出当前完整的计划数据' for exporting complete plan data) and mentions its relationship with loadPlan for state restoration, providing clear context. However, it doesn't specify when NOT to use it or explicitly contrast it with alternatives like getPlanStatus or getTaskList that provide partial plan information.

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

• skipTaskA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses key behavioral traits: the skipped status affects dependency resolution (treating skipped tasks as 'completed'), which is crucial context. However, it doesn't mention permissions needed, whether the action is reversible, or what happens if the task_id doesn't exist.

  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 perfectly structured with a clear purpose statement followed by a well-organized parameter section. Every sentence earns its place, with no wasted words. The bilingual format (Chinese with English parameter names) is efficient and clear.

  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 mutation tool with no annotations and no output schema, the description provides adequate basics but lacks completeness. It explains what the tool does and its parameters well, but doesn't cover error conditions, return values, or system state changes beyond the dependency resolution effect mentioned.

  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 both parameters clearly. It specifies task_id is an integer starting from 0, and reason is a string explaining why the task is skipped. This adds essential meaning beyond the bare schema.

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

  Purpose5/5

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

  The description clearly states the specific action ('标记为 skipped' - mark as skipped) on a specific resource ('指定ID的任务' - task with specified ID). It distinguishes from siblings like completeTask and failTask by specifying the unique 'skipped' status and its effect on dependency resolution.

  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 about when to use this tool: when a task needs to be marked as skipped to allow dependent tasks to proceed. It doesn't explicitly state when NOT to use it or name specific alternatives, but the context is sufficient for understanding its role among sibling tools like completeTask and failTask.

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

• editDependenciesA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: batch/transactional nature, validation before application, and atomic rollback on failure. It also explains the two operation modes ('set' vs 'update'). However, it doesn't mention permission requirements, rate limits, or what happens to existing dependencies during updates.

  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 clear purpose statement followed by detailed parameter documentation. Every sentence adds value, though the parameter section is quite detailed (which is necessary given the 0% schema coverage). The information is front-loaded with the most important behavioral characteristics first.

  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 mutation tool with no annotations and no output schema, the description provides substantial context about behavior, parameters, and transactional guarantees. It covers the essential aspects well, though it could benefit from mentioning return values or error responses since there's no output 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?

  With 0% schema description coverage, the description fully compensates by providing comprehensive parameter documentation. It explains the structure of the 'edits' list, defines all fields (task_id, action, dependencies, add, remove), clarifies when each optional field is required based on action type, and provides semantic meaning beyond basic types.

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

  Purpose5/5

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

  The description clearly states the tool's purpose with specific verbs ('edit dependencies') and resources ('tasks'), and distinguishes it from siblings by emphasizing batch/transactional operations. It explicitly mentions 'set' and 'update' actions, which differentiates it from tools like addTask or completeTask that handle different task modifications.

  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 for when to use this tool (batch/transactional dependency editing) and implicitly distinguishes it from single-task operations. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools (like whether visualizeDependencies is complementary or when to use addTask instead).

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

• startNextTaskA
  4.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it mutates state (updates task status to 'in_progress'), finds tasks based on dependency completion, and returns a TaskOutput object. However, it lacks details on error conditions (e.g., if no executable tasks exist), side effects, or permissions needed. It adds value but is not comprehensive.

  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 core action in the first sentence, followed by state change and purpose context, ending with return value details. Every sentence adds value: the first explains what it does, the second clarifies the mutation, the third provides usage context, and the fourth specifies the output. No wasted words.

  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 complexity (a state-mutating tool with no annotations and no output schema), the description is mostly complete. It covers purpose, usage, behavior, and output type. However, it lacks error handling or edge case details (e.g., what happens if no tasks are executable), which would be helpful for full contextual understanding.

  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 0 parameters, and schema description coverage is 100%, so the baseline is 4. The description appropriately does not discuss parameters, as none exist, and focuses on the tool's action and output instead.

  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 specific action ('自动查找下一个可执行的任务并开始执行') and the resource ('任务'), distinguishing it from siblings like getExecutableTaskList (which only lists) or getCurrentTask (which retrieves without starting). It explicitly mentions updating task status to 'in_progress', which further clarifies its distinct 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?

  The description provides explicit guidance on when to use this tool: when dependencies are completed ('所有依赖均已完成') and to advance the plan ('推进计划的核心方法'). It implicitly distinguishes from alternatives like getExecutableTaskList (for listing only) or completeTask/failTask/skipTask (for ending tasks). The context is clear without exclusions.

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