Server Quality Checklist

Tool Scores

• get_progressC
  2.9/5.0
  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 only states the tool queries progress and requires session input, without describing what 'progress' means (e.g., percentage, status, next steps), whether it's read-only (implied but not explicit), what happens if the session is invalid, or any error conditions. For a tool with no annotations, this leaves significant behavioral 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 appropriately concise with two short sentences that state the purpose and parameter requirement without unnecessary details. It's front-loaded with the main function. However, it could be slightly more structured by explicitly separating purpose from requirements, but it remains efficient with zero waste.

  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?

  Given the complexity (1 parameter with nested object, no output schema, no annotations), the description is incomplete. It doesn't explain what 'progress' entails (e.g., a percentage, status message, or structured data), how the session properties influence the output, or any error handling. Without annotations or output schema, the description should provide more context about the tool's behavior and results, but it falls short.

  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?

  The description adds minimal value beyond the input schema, which has 100% coverage. It mentions that a test session state is required, aligning with the schema's 'session' parameter description ('测试会话状态'). However, it doesn't explain what 'progress' means in relation to the session properties (testType, answers, currentQuestionIndex) or how these affect the query. With high schema coverage, the baseline is 3, and the description doesn't significantly enhance parameter understanding.

  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 as '查询当前测试进度' (query current test progress), which is a specific verb+resource combination. It distinguishes itself from siblings like 'start_mbti_test' (initiation) and 'calculate_mbti_result' (final calculation), though it doesn't explicitly differentiate from 'answer_question' which might be related but serves a different function. The purpose is clear but lacks explicit sibling differentiation.

  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 that a test session state is required ('需要传入测试会话状态'), but this is more of a parameter requirement than usage context. There's no indication of when this tool should be called during a test flow, what prerequisites exist, or how it relates to sibling tools like 'answer_question' or 'calculate_mbti_result'.

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

• answer_questionB
  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 full burden. It mentions the tool submits an answer and gets next question/progress, but doesn't disclose important behavioral traits: whether this is a read-only or mutating operation (likely mutating since it submits answers), what happens to the session state after submission, error conditions (e.g., invalid score range), or response format. For a tool that appears to update test progress with no annotation coverage, this is a significant gap.

  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 a single sentence that efficiently conveys the core functionality. It's front-loaded with the primary action and outcome. Every element earns its place, though it could potentially benefit from slightly more detail given the lack of annotations.

  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?

  Given the tool's apparent complexity (mutating test state, no output schema, no annotations), the description is insufficient. It doesn't explain what the tool returns (next question? updated progress? confirmation?), error handling, or behavioral implications. For a tool that seems to advance a test session and update answers, more context about the operation and results is needed.

  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 100%, so the schema already documents both parameters thoroughly. The description adds minimal value beyond the schema, only mentioning that the session parameter should be '完整的测试会话状态' (complete test session state), which is already implied by the schema's required fields. No additional syntax, format details, or constraints are provided beyond what's in 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 action ('提交当前问题的答案' - submit current question answer) and resource ('获取下一题或测试进度' - get next question or test progress). It distinguishes from siblings by focusing on answering questions within a test session, unlike 'calculate_mbti_result' (calculates final result), 'get_progress' (likely retrieves progress), or 'start_mbti_test' (initiates test). However, it doesn't explicitly name the test type (MBTI) which would make it more specific.

  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 ('当前问题' - current question, '测试会话状态' - test session state) suggesting it should be used during an active test session. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'get_progress' for checking progress without answering, or 'calculate_mbti_result' for final calculation. 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.

• calculate_mbti_resultB
  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 full burden for behavioral disclosure. It states the calculation action but doesn't describe what '详细结果' (detailed results) includes, whether this is a read-only computation or creates persistent data, error conditions, or performance characteristics. The description provides minimal behavioral context beyond the basic purpose.

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

  Conciseness5/5

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

  The description is extremely concise with just two sentences that directly address purpose and parameter requirements. Every word earns its place with no redundancy or unnecessary elaboration. It's front-loaded with the core purpose followed by the key requirement.

  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?

  For a calculation tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what '详细结果' (detailed results) includes, the format of the MBTI type output, potential error conditions, or whether this operation has side effects. Given the complexity of MBTI calculation and lack of structured output documentation, more context is needed.

  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 100%, so the schema already documents the single 'session' parameter and its required nested properties. The description adds that the session must contain '所有题目的答案' (all question answers), which provides useful semantic context about completeness requirements, but doesn't significantly expand beyond what the schema provides. Baseline 3 is appropriate given high schema coverage.

  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: '根据所有答案计算最终的MBTI类型和详细结果' (calculate final MBTI type and detailed results based on all answers). It specifies the verb '计算' (calculate) and resource 'MBTI类型和详细结果' (MBTI type and detailed results), but doesn't explicitly differentiate from sibling tools like 'get_progress' or 'answer_question' beyond implying this is the final calculation step.

  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 provides implied usage context: '需要传入完整的测试会话状态' (requires passing complete test session state), suggesting this should be used when all answers are available. However, it doesn't explicitly state when to use this vs. alternatives like 'get_progress' for intermediate results or 'start_mbti_test' to begin, nor does it mention prerequisites or exclusions.

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

• start_mbti_testA
  3.5/5.0
  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 starts a test, returns the first question and session state, and supports two test types. However, it lacks details on error handling, session management (e.g., expiration), or performance aspects like rate limits, which are important for a tool initiating a test.

  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, consisting of two clear sentences. The first sentence states the purpose and parameter options, and the second explains the return value. Every sentence earns its place with no wasted words, making it efficient and easy to understand.

  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 (initiating a test with one parameter) and no annotations or output schema, the description is somewhat complete but has gaps. It covers the purpose, parameter options, and return value, but lacks details on error cases, session lifecycle, or how outputs relate to sibling tools, which could hinder an agent's effective use.

  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?

  The schema description coverage is 100%, with the single parameter 'testType' fully documented in the schema (including enum values and descriptions). The description adds minimal value beyond the schema by mentioning the test types and their question counts, but it doesn't provide additional semantic context (e.g., differences between test versions). Baseline 3 is appropriate as the schema does the heavy lifting.

  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 with a specific verb ('开始MBTI人格测试') and resource (MBTI test), and it mentions the two test type options. However, it doesn't explicitly distinguish this tool from its siblings (e.g., answer_question, calculate_mbti_result, get_progress), which would require clarification on when to use each in the test flow.

  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 at the start of an MBTI test by stating it '返回第一道题目和测试会话状态,' suggesting it initiates the test. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like get_progress or how it fits into the overall test workflow with siblings, leaving some ambiguity.

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