Server Quality Checklist

Tool Scores

• list_dangerous_opsB
  3.2/5.0
  Behavior2/5

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

  No annotations provided, and the description does not disclose behavioral traits such as whether the operation is read-only, requires authentication, or has rate limits. Short description lacks necessary 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?

  Single sentence with no extraneous information. Efficiently conveys the essential purpose.

  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 tool with no parameters and no output schema, the description is minimally complete. It explains what is listed and its relation to 'assess_and_gate', but lacks details on read-only nature or catalog dynamics.

  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?

  No parameters exist, so baseline score of 4 applies. The description does not add any parameter-level detail beyond the 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 lists a 'built-in dangerous operation catalog' and ties it to 'assess_and_gate', which distinguishes it from sibling tools focused on approval workflows. However, it does not describe the catalog's format or contents.

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

  Usage Guidelines2/5

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

  No guidance on when to use this tool versus alternatives. The description only notes that the catalog is 'used by assess_and_gate', implying reference use, but no explicit when-to-use or when-not-to-use.

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

• list_pendingB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description should explicitly state behavioral traits. It does not mention whether the operation is read-only, any authentication needs, pagination, or rate limits. The description is too brief to inform safe usage.

  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?

  A single sentence that is efficient and front-loaded with the key action and resource. No extraneous words.

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

  Completeness2/5

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

  The description lacks crucial context: it does not specify the output format (e.g., list of IDs, full objects), scope (user-specific or global), or any prerequisites. Given no output schema and no annotations, the description should compensate.

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

  Parameters4/5

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

  There are zero parameters, so baseline 4 applies. The description does not need to add parameter information, and the schema coverage is 100% trivially.

  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 'List' and the resource 'pending approval tickets waiting for human decision,' which is specific and distinct from sibling tools like list_approval_history or get_approval_status.

  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. For example, it does not mention that this shows only pending items while list_approval_history shows all statuses, or when to use request_approval instead.

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

• request_approvalA
  3.6/5.0
  Behavior2/5

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

  No annotations provided; description fails to disclose behavioral traits like destruction potential, permissions, response format, or process details 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?

  Two sentences, clear and front-loaded, but slightly verbose with internal implementation detail ('Cursor elicitation').

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

  Completeness2/5

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

  Complex tool (6 params, nested objects, no output schema) but description omits output, error handling, and behavior after request.

  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 coverage is 33%; description adds no meaning to any of the 6 parameters, does not compensate for undocumented params.

  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?

  Describes requesting human approval and skipping assessment, clearly distinguishes from sibling 'assess_and_gate'.

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

  Usage Guidelines5/5

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

  Explicitly states when to use (skip assessment) and when to prefer alternative (assess_and_gate for normal flow), plus mentions Cursor elicitation condition.

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

• get_approval_statusA
  3.8/5.0
  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 explaining behavioral traits. It reveals that the tool returns a status string and that the agent must conditionally act on it. This is adequate for a simple read operation, though it could mention error handling for invalid ticket_ids.

  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 sentences, front-loaded with key information, and contains no unnecessary words. Every part serves a purpose: identifying the tool and providing action criteria.

  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 that there is no output schema, the description should explicitly state the possible return values (e.g., 'approved', 'rejected', 'expired') and the output format. It implies these values but does not specify them, leaving some ambiguity about the exact response structure.

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

  Parameters1/5

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

  The input schema has 0% description coverage and the tool description does not add any meaning to the single parameter 'ticket_id'. It does not explain what the parameter represents or provide any formatting guidance, leaving the agent to rely solely on the parameter name.

  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 ('get') and resource ('approval ticket status'), and provides conditional guidance on how to use the result. It distinguishes from sibling tools like list_pending and request_approval, which serve different purposes.

  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 tells the agent when to proceed (if status is approved) and when to stop (if rejected or expired), giving clear context for decision-making. However, it does not mention when to use this tool over alternatives, such as assess_and_gate or list_pending.

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

• list_approval_historyA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description should carry full behavioral disclosure. It does not explicitly state that the tool is read-only or safe, nor does it mention side effects, permissions, or rate limits. The instruction to 'Present summary_zh in chat' implies output handling but not behavioral constraints.

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

  Conciseness5/5

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

  The description is two sentences: the first defines the tool's core action, the second adds usage guidance and a post-call instruction. Every phrase serves a purpose, and the most critical information is front-loaded.

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

  Completeness4/5

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

  Given the tool's simplicity (two optional parameters, no output schema), the description covers the purpose, trigger phrases, and a key response field (summary_zh). However, it does not describe the full return format or pagination behavior, which would be helpful but not essential.

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

  Parameters3/5

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

  Schema coverage is 100%, so the baseline is 3. The description merely restates the optional status filter and limit without adding new semantics or examples beyond what the schema provides.

  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 specifies the action (list) and the resource (approval audit history for the user). It explicitly mentions trigger phrases (看审批记录, view approval history, audit log) and instructs to present summary_zh, leaving no ambiguity about the tool's function.

  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 states when to call the tool ('when the user asks to...'). However, it does not explicitly exclude cases where alternative tools (e.g., get_approval_status, list_pending) would be more appropriate, nor does it compare to siblings.

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

• assess_and_gateA
  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 full burden. It discloses the workflow (assess, then if dangerous create ticket and await approval), and warns not to execute while pending/rejected. However, it does not describe the assessment criteria or the exact output format beyond 'approved/rejected'.

  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 paragraph that conveys all essential information with no wasted words. It front-loads the core action: assess and gate.

  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 policy gate tool with 6 parameters and no output schema, the description covers the essential workflow and constraints. It lacks details on return values and synchronization behavior, but is sufficient for guiding agent decisions.

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

  Parameters3/5

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

  Schema description coverage is 67%, so baseline is 3. The description adds context for 'intent' (the user request) but does not explain 'action', 'params', 'requester', 'auto_create', or 'ttl_seconds' beyond what the schema already provides.

  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 assesses risk and gates dangerous actions by creating a ticket and requesting approval. It uses specific verbs like 'assess risk' and 'create a ticket', and the distinction from siblings (which are query tools) is implicit but clear.

  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?

  Explicitly advises to 'Call BEFORE side effects' and 'Do NOT execute while pending/rejected', providing clear when-to-use and when-not-to-use guidance. It also mentions a fallback, but does not explicitly list alternatives to this tool vs siblings.

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