Server Quality Checklist

Tool Scores

• advisor_pollA
  3.7/5.0
  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 of behavioral disclosure. It discloses the three possible outcome types (running with elapsed time, result, failed), which is useful for an agent to interpret the response. However, it does not cover edge cases like invalid task_id or timeout behavior, but overall it provides meaningful 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 a single concise sentence with an emoji list, front-loading the action and clearly enumerating states. Every element adds value, and there is no redundant or extraneous text.

  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 tool is simple (one required parameter) and has an output schema, so the description does not need to detail return values. The description adequately conveys the purpose and expected outcome types, making it complete enough for basic usage. It could mention polling behavior (e.g., whether it is non-blocking), but the context is sufficient for a straightforward status query.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description does not explicitly describe the task_id parameter. The parameter name is self-explanatory and its usage is implied by the description ('query status'), but the description does not add any specific details about format, expected values, or how to obtain it. This is a minor gap.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: querying the status of a consultation task. It lists the possible statuses (running with elapsed time, result, failed), and the verb '查询' is specific. This distinguishes it from sibling tools like advisor_create_task (creation) and advisor_list_tasks (listing).

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives. It does not mention that it should be used after creating a task or how it differs from advisor_list_tasks. The name 'poll' implies usage, but explicit exclusions or alternatives are absent.

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

• advisor_create_taskA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral disclosure burden. It reveals key behaviors: existing bindings are reused and renamed, while force_new=True creates a new kimi session. It also imposes a naming constraint (task_name in short Chinese). It does not mention side effects like overwriting, but the primary behaviors are disclosed.

  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, dense sentence that front-loads the core purpose and packs in behavioral rules and naming guidance. Every clause adds value, with no redundancy or wasted words.

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

  Completeness3/5

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

  The description covers the main workflow (reuse vs new session) and partially explains parameters, but it omits clarification for goal and context, which are important for usage. The output schema exists, so return values are covered, but the tool's integration with the current conversation and its relation to sibling tools could be more explicit. Overall, it is adequate but has clear gaps.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate. It explicitly explains task_name (use short Chinese name) and force_new (only opens new session when true), but provides no meaning for goal or context. With 4 parameters, only half are semantically clarified, leaving required goal and optional context ambiguous.

  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 '登记当前对话的顾问咨询' clearly states a specific verb and resource: registering the current conversation's advisor consultation. It distinguishes from siblings by describing the registration/create behavior and the reuse/new-session logic, which is not mentioned for other 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 gives clear context: register the advisor consultation for the current conversation. It also provides a specific usage rule for force_new ('已有绑定则复用(改名),force_new=True 才新开 kimi 会话'), explaining when to set the flag. It does not explicitly contrast with alternatives, but the context is clear enough.

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

• advisor_list_tasksA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It indicates a list operation (implying read-only), but does not explicitly mention side-effect-free behavior, error conditions, or what 'kimi 会话' entails. It adds scoping info ('本工程'), but lacks richer 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 a single concise sentence that front-loads the verb '列出' and includes all essential information without waste. It is efficiently structured and easy to parse.

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

  Completeness4/5

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

  For a simple parameterless list tool with an output schema, the description is sufficiently complete—it states the resource, scope, and displayed fields. It slightly lacks usage guidance but otherwise covers the tool's purpose adequately.

  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 there are no param semantics to clarify. Per the rubric, a baseline of 4 is appropriate when no parameters exist, and the description does not mislead about parameters.

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

  Purpose5/5

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

  The description clearly states the tool lists advisor session bindings for the current project, specifying the fields included (session name / status / kimi session). The verb '列出' (list) and resource '顾问会话绑定' are specific, and it is clearly distinct from sibling create, consult, poll, and close operations.

  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 for viewing existing session bindings, but provides no explicit guidance on when to use this versus alternatives. No when-not-to-use or alternative comparisons are given, leaving the usage context implicit.

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

• advisor_close_taskA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full transparency burden. It discloses a key behavior: the session is retained on the Kimi side for review, which is valuable context. However, it does not mention idempotency, permissions, or effects on pending operations, leaving some gaps.

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

  Conciseness5/5

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

  The description is a single, dense sentence that front-loads the core action and includes the key behavioral caveat. No unnecessary words or repetition, achieving excellent conciseness.

  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 simple one-parameter tool and the presence of an output schema, the description covers the essential information: the action, the parameter semantics, and the retention behavior. It could mention error scenarios or prerequisites, but these are not critical for this straightforward operation.

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

  Parameters4/5

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

  Schema coverage is 0%, so the description must compensate. It clarifies that task_id is optional and that omitting it targets the current conversation, adding meaning beyond the bare schema. This is sufficient for a single optional parameter.

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

  Purpose5/5

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

  The description clearly states the action: marking an advisor session as complete, with a specific resource (advisor session) and an optional task_id parameter. It distinguishes itself from sibling tools (create, consult, poll, list) by focusing on the closing action.

  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 'current conversation or task_id specified', but it does not explicitly state when to prefer this tool over siblings or any exclusions. No clear 'when to use' or 'when not to use' guidance is provided.

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

• advisor_consultA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It discloses async behavior, immediate return of task number, and the ability to specify task_id for other sessions. However, it does not mention side effects, permissions, or whether the consult is read-only or creates persistent artifacts, leaving some ambiguity.

  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, with a single sentence containing all essential information: async flow, follow-up, mode options, and task_id usage. It is front-loaded and every clause adds value.

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

  Completeness4/5

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

  For a simple async tool with an output schema, the description covers the key workflow, modes, and task_id semantics. It lacks explicit error handling or prerequisites, but these are not critical given the tool's straightforward nature.

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

  Parameters4/5

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

  Schema coverage is 0%, but the description explains two of three parameters: mode (with enumerated values) and task_id (for other sessions). The message parameter is self-explanatory, so the description meaningfully compensates for the schema's lack of 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 it initiates an asynchronous consultation and immediately returns a task number. It distinguishes from siblings by directing the user to advisor_poll for results, and the mode options (blueprint/unstick/review) clarify the tool's specific role.

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

  Usage Guidelines4/5

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

  The description gives clear follow-up guidance (use advisor_poll to check results) and explains the mode options, providing context for when to use this tool. However, it doesn't explicitly contrast with siblings like advisor_create_task, though the async consult purpose is evident.

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