Server Quality Checklist

Tool Scores

• list_processed_workflowsB
  3.3/5.0
  Behavior2/5

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

  No annotations are supplied, so the description carries the full burden of behavioral disclosure. It only states that the tool returns a JSON string and mentions arguments; it does not explicitly state that the operation is read-only, how pagination behaves, what 'archived' means, or what errors or edge cases to expect.

  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 purpose statement followed by Args and Returns sections. The argument details are concise and easy to scan. The first sentence is slightly redundant with the second, but the overall structure is 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 output schema exists and all parameters are described, the core invocation details are covered. However, with no annotations and several overlapping sibling tools, the description is missing guidance on alternatives and deeper behavioral context, leaving the agent to infer when this specific list is appropriate.

  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%, but the description compensates by explaining every parameter: page_no starts at 1, page_size is per-page count, workflow_id defaults to the default configuration when blank, and all_types returns all workflow types when True. This adds meaning well beyond the bare schema titles.

  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 identifies the tool as retrieving a list of '已办（归档）流程' (processed/archived workflows) and further restricts it to '当前用户已处理' (current user's processed items). This gives a specific verb, resource, and scope, but it doesn't explicitly contrast the tool with sibling tools like list_todo_workflows or list_all_workflows.

  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 implies the tool is for a current user's processed/archived workflows, but it provides no explicit guidance on when to choose this tool over siblings such as list_todo_workflows, list_my_workflows, or list_all_workflows. There are no exclusion criteria or alternative recommendations.

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

• list_todo_workflowsA
  3.6/5.0
  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 clarifies that the tool returns a JSON string and explains the all_types filtering behavior, but it does not explicitly state side effects, authorization requirements, pagination semantics, or error behavior. This is adequate for a read-style list tool but not fully transparent.

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

  Conciseness4/5

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

  The description is compact and logically structured: a direct headline, a fuller purpose statement, parameter explanations, and a return note. There is minor redundancy between the first line and the second, but the overall structure is clear and efficient.

  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 straightforward list tool with four optional parameters and an output schema available, the description covers purpose, parameter semantics, and return format. It would be more complete with explicit selection guidance against sibling tools, but the core calling context is adequately addressed.

  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 fully compensates by explaining every parameter: page_no starts at 1, page_size is items per page, workflow_id is a template ID with default behavior, and all_types changes filtering behavior. This adds real meaning beyond the bare schema titles and defaults.

  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 a specific action and scope: '获取当前用户待处理的流程列表' (get the current user's pending workflow list). It is distinguishable from siblings like list_processed_workflows and list_all_workflows by the 'pending/current user' framing, but it does not explicitly name or differentiate those siblings.

  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 explains what the tool does but gives no guidance on when to choose it over list_my_workflows, list_processed_workflows, list_all_workflows, or other siblings. There are no explicit usage conditions, exclusions, or alternative recommendations.

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

• get_workflow_detailA
  3.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It discloses that the operation returns a JSON string containing form field values, approval opinions, and routing logs, and it explains what the two boolean flags toggle. It does not mention error cases, permissions, or side effects, but the read-only nature is clearly indicated by '获取'.

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

  Conciseness4/5

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

  The description is well structured: a purpose statement, an Args block, and a Returns block. Information is front-loaded and each section has a clear role. The first line merely repeats the tool name and the 'core interface' sentence is mildly promotional, but the overall density is good.

  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 3 parameters, no annotations, and the presence of an output schema, the description is largely complete: it covers parameter semantics, the source of request_id, and the general return content. It could add guidance on when to set the booleans false or how to handle errors, but those are minor gaps for a read-only detail lookup.

  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 description coverage is 0%, and the description compensates in the Args section. It explains that request_id comes from the workflow list's requestid field and clarifies the meaning and defaults of is_get_form_data and is_get_request_log. Some details, like the booleans' defaults, are redundant with the schema, but the added semantics are non-obvious and useful.

  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 states a specific verb and resource: '获取流程详情' and '根据流程请求ID获取流程的详细信息，包括表单数据、审批记录等'. It also identifies itself as the core interface for getting program modification content. However, it does not explicitly disambiguate from the sibling get_program_modification_details, so it stops short of a 5.

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

  Usage Guidelines3/5

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

  The description implies usage context well: the request_id should come from the workflow list's requestid field, and this tool is the core way to get the actual modification content. But it never explicitly states when not to use it, what conditions select this tool over sibling list/detail tools, or any exclusions.

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

• list_all_workflowsA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral burden. It discloses current-user scoping, default workflow_id behavior, all_types override behavior, date-range options, and that the return value is a JSON string. It does not mention potential errors or rate limits, but the read-only fetch nature is clear from the verb '获取'.

  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 Args-style structure is clean and front-loaded with the tool's purpose. There is minor redundancy between the first two sentences, both stating the 'all workflows list' idea, but the content is otherwise efficient and well-organized.

  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 is largely complete for invoking the tool: it covers all parameters, provides known IDs, explains filtering behavior, and notes the return type. An output schema exists, so detailed return-field documentation is not required. The main gap is the lack of explicit guidance on how this tool relates to the sibling workflow-list tools.

  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%, and the description fully compensates by explaining every parameter: page_no, page_size, date_range with enumerated allowed values, workflow_id with known process type IDs, and all_types semantics. This adds substantial meaning beyond the bare schema names and defaults.

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

  Purpose5/5

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

  The description clearly states the operation: '获取当前用户可见的所有流程列表' (get all workflows visible to the current user), supported by type/date filtering. The 'all' scope distinguishes it from sibling list tools focused on my/todo/processed/program-modification workflows. The verb and resource are specific and unambiguous.

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

  Usage Guidelines3/5

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

  The description conveys the tool's context—listing all workflows visible to the current user—but does not explicitly state when to prefer this tool over list_my_workflows, list_todo_workflows, list_processed_workflows, or get_workflow_detail. Usage must be inferred from the name and scope rather than stated directly.

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

• list_my_workflowsA
  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 the behavioral burden. It discloses the return format as a JSON string and explains the all_types parameter's effect. However, it does not mention auth requirements, error behavior, ordering, or explicitly confirm read-only status, leaving some transparency gaps.

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

  Conciseness4/5

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

  The description is compact and well-structured, with a clear Args section. The first sentence '获取我的请求流程列表' is somewhat redundant with the tool name, but the following sentence adds meaningful scope, so there is only minor waste.

  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 4 undocumented parameters, no annotations, and multiple sibling list tools, the description provides adequate parameter semantics and return information. It lacks explicit sibling differentiation and behavioral caveats, but an output schema exists, reducing the need to describe return values in detail.

  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%, yet the description fully compensates by explaining all four parameters: page_no starts at 1, page_size controls count, workflow_id defaults to a configured template when empty, and all_types=true returns all workflow types. This goes well 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 states a specific verb and resource: '获取当前用户发起的流程列表' (get workflows initiated by the current user). This clearly distinguishes the tool from siblings like list_all_workflows, list_todo_workflows, and list_processed_workflows by defining the exact scope.

  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 clearly indicates when to use the tool: when the current user's own initiated workflows are needed. It does not explicitly name alternatives or provide when-not-to-use guidance, but the scope is clear enough for an agent to select it among the sibling list tools.

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

• list_program_modification_workflowsA
  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 behavioral burden. It discloses the non-obvious server-side 'configured workflowid' behavior, describes the returned item fields, and documents date_range filter semantics. It does not mention errors, authentication, or pagination metadata, but for a read-only listing these are relatively minor gaps.

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

  Conciseness4/5

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

  The description is compact and front-loaded with a one-line summary, followed by concise Args and Returns sections. There is slight redundancy between the statement that each workflow contains requestId and the Returns line saying the JSON contains a requestId list, but this does not meaningfully bloat the description.

  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 tool with three optional parameters and an output schema, the description is nearly complete. It documents every parameter, defaults, filter values, and returned fields. The only notable gap is that the 'configured workflowid' is not explained in terms of where that configuration lives, but this is minor given the low complexity.

  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 property descriptions are absent (0% coverage), and the description fully compensates. It states page_no starts at 1 and defaults to 1, page_size defaults to 20, enumerates all date_range allowed values, and explains that leaving date_range blank disables date filtering.

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

  Purpose5/5

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

  The description opens with '查询程序修改流程列表' and clarifies that it lists all workflow instances for the configured program-modification workflow type. It gives a clear verb+resource and distinguishes itself from get_program_modification_details by noting each returned item includes a requestId used to fetch details.

  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 scope is implied: the tool lists program-modification workflow instances using a configured workflowid, so the use case is inferable. However, it gives no explicit guidance about when to prefer this over sibling tools like list_my_workflows or list_all_workflows, and no exclusions are stated.

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

• get_program_modification_detailsA
  4.5/5.0
  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 that the tool performs a multi-step read operation (query list, then batch-fetch details) and returns a JSON string. It also explains why the default page_size is 5 ('避免请求过多'), adding useful behavioral context beyond the schema.

  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 well-structured: purpose, workflow behavior, then args and return type. Each sentence adds value, and the key information is front-loaded. There is no repetition of schema fields beyond useful semantic annotations.

  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 two-parameter composite read tool, the description covers the operation, argument semantics, and return format sufficiently, especially given that an output schema is indicated. It could be slightly stronger by explicitly routing to sibling tools for single-step needs, but nothing critical is missing for correct invocation.

  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%, but the description fully compensates by documenting both parameters: page_no starts at 1, and page_size has a default of 5 with a rationale. This gives the agent the semantic meaning needed to invoke the tool correctly, which the bare input schema lacks.

  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 and resource: '获取程序修改流程列表及其详情' (get program modification workflow list and its details), and explicitly identifies it as a combined query. This clearly distinguishes it from siblings like list_program_modification_workflows and get_workflow_detail by covering the whole list→detail flow in one call.

  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 clearly conveys that this tool is for when you need both the list and the details, describing the automatic 'list → ID → detail' flow. It does not explicitly name alternatives or state when not to use it, but the combined-query framing makes the intended usage context clear.

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

• query_employeeA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral burden and mostly delivers: it discloses matching semantics ('姓名模糊查询或账号精确查询' — fuzzy vs exact), the return shape (JSON containing id/userId, username, job_num), and the default page_size of 50. It omits edge behaviors such as what happens when both or neither filter is supplied, which keeps it from a 5.

  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 tight and well-structured: a one-line purpose statement, a two-line behavior note, then clearly separated Args and Returns sections. Each sentence carries distinct information (purpose, matching behavior, downstream use, parameter semantics, return format) with no filler or repetition.

  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 3-parameter read-only query with an output schema present, the description covers purpose, all parameter semantics, return content, and downstream usage. The only gaps are edge-case behavior (no filters supplied, both filters supplied) and pagination semantics beyond the default, which are minor for this tool.

  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 compensate — and it documents all three parameters with meaning beyond the bare schema: name_like supports fuzzy matching, account is explicitly '登录名/手机/邮箱' (login name/phone/email), and page_size has a stated default of 50. Every parameter receives semantic context the schema lacks.

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

  Purpose5/5

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

  The description opens with a specific verb+resource — '查询泛微 E10 人员信息' (query Weaver E10 personnel) — then specifies the two query modes (fuzzy by name, exact by account) and the key return value (userId). The resource is personnel, which is unambiguous against the eight workflow/sibling tools, and the note that 'userId 用于流程列表和流程详情查询' situates it as the lookup step before workflow queries, further distinguishing it from the workflow siblings.

  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 for when to call this tool: userId is needed for workflow list/detail queries ('userId 用于流程列表和流程详情查询'), implying this is the prerequisite lookup for the workflow sibling tools. It does not, however, explicitly state when not to use it or name an alternative, so it falls short of a 5.

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

• submit_work_reportA
  4.5/5.0
  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 the mutation (create + submit), auto-filling of fields, month-dependent default behavior, and the return format (JSON with requestId). It does not mention permissions or failure modes, but the core behavioral contract is transparent.

  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 in listed sections (Args, Returns) with no fluff. Every sentence adds value: process overview, parameter details, and return format. Front-loaded with the action, then details follow logically.

  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 3-parameter mutation tool with no annotations, the description is fairly complete: it covers all parameters, the auto-fill behavior, and the return. It lacks explicit prerequisites (e.g., authentication or existing project setup), but the auto-fill hints that context is supplied elsewhere. The presence of an output schema further reduces the need to detail return values.

  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 compensate, and it does thoroughly. It explains report_date format (YYYY-MM-DD), work_content default logic with explicit month ranges, and project_hours default (8). This goes well beyond the schema, which only names the parameters without hints.

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

  Purpose5/5

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

  The description opens with a specific verb phrase '创建并提交一条研发报工' (create and submit a research work report), naming both the action and the resource. It distinguishes itself from all sibling tools, which are all query/workflow-oriented, by being the only submission tool.

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

  Usage Guidelines4/5

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

  The usage context is clear: it creates and submits a work report, with automatic field population. It also explains the month-based auto-selection of work content and the option to override it manually. However, it does not explicitly state when not to use it, though no sibling competes for this exact task.

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

• test_connectionA
  4.5/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries the behavioral disclosure burden. It explains that the tool attempts to obtain an access_token and returns server information, which accurately implies a read-only connectivity check. It does not detail error behavior, but that is minor for this simple diagnostic 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 only two concise sentences, with the core purpose front-loaded and a supporting detail following. Every sentence adds useful information with no repetition or filler.

  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 diagnostic tool that has an output schema, the description fully explains the action taken and the intended use case. An agent has everything it needs to invoke and interpret this 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 no parameters, so the description need not explain parameter semantics. The schema already documents the empty argument list with 100% coverage, so 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 states a specific verb, '测试' (test), and a specific resource, the connection to 泛微 OA, and further clarifies the mechanism by attempting to obtain an access_token. This clearly distinguishes it from the data/workflow 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 gives clear context: use this to verify that the configuration is correct. It does not explicitly list alternatives or when not to use it, but the zero-parameter diagnostic purpose makes the appropriate usage obvious relative to the siblings.

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