Server Quality Checklist

Tool Scores

• get_project_detailC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description must fully disclose behavior. It only states 'get project detail', implying a read operation but does not explicitly confirm it is read-only, nor does it mention any required permissions, side effects, or edge cases. This is insufficient given the lack of annotations.

  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 a single sentence with no wasted words. However, it is underspecified; conciseness is good but the content could be expanded slightly to improve clarity without becoming verbose.

  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 absence of an output schema, the description should at least hint at what 'detailed information' includes (e.g., project fields, members, etc.). It does not, leaving the agent uncertain about the return value. With sibling tools providing similar patterns, the description is incomplete for the agent to fully understand the tool's scope.

  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 input schema covers 100% of the single parameter 'pno', and the description adds no additional meaning beyond the schema's own description '專案編號'. Since schema coverage is high, the baseline score of 3 is appropriate; the description does not 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 '取得專案詳細資訊' clearly conveys that the tool retrieves detailed information for a specific project, matching the tool name 'get_project_detail'. However, it does not differentiate from sibling tools like 'list_projects' which may return summary data. The purpose is clear but lacks explicit distinction.

  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 such as 'list_projects' or 'get_requirement_detail'. There is no mention of prerequisites or context, leaving the agent without decision support.

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

• list_bugsC
  2.9/5.0
  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. It only states that the tool queries a bug list. It does not disclose pagination behavior, default sorting, error handling, or whether results are limited or ordered. For a read operation, this is insufficient to set agent expectations.

  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 a single concise sentence that immediately conveys the core action and resource. It is front-loaded with the verb and object. While it could include more information without becoming verbose, it avoids any unnecessary words or repetition.

  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 that there is no output schema, the description should clarify what the tool returns (e.g., a list of bug objects, paginated results, empty array). It does not. The description also lacks contextual details like sorting order or default pagination values. For a simple list tool with three parameters, the description is incomplete.

  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 input schema has 100% description coverage for all three parameters (pno, page, limit), each with a clear label in Chinese. The tool description does not add any additional semantic value beyond what the schema already provides. Baseline score of 3 is appropriate when schema fully documents parameters.

  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 '查詢' (query) and the resource '缺陷清單' (defect list) scoped to a specific project. It distinguishes the tool from sibling tools like create_bug or update_bug by focusing on listing, but does not explicitly differentiate from other list tools like list_requirements or list_todos. The purpose is clear and specific.

  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 (e.g., create_bug for new bugs or search tools). There is no indication of prerequisites, limitations, or contextual usage advice. An agent would need to infer usage from the tool name alone.

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

• list_sprintsC
  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 full burden for behavioral disclosure. It does not state read-only nature, performance characteristics, or any edge-case behaviors (e.g., empty sprint list, error on invalid pno). The agent must infer safety from the verb '查詢' (query), which is implicit.

  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 a single, direct sentence that conveys the tool's purpose without unnecessary words. It could be slightly longer to add usage guidelines or transparency details, but it is concise and front-loaded.

  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 has one required parameter and no output schema, the description is too minimal. It lacks context about the return format (e.g., sprint IDs, dates) and does not compensate for the absent output schema. The agent is left to guess what fields are in the sprint list, which is insufficient for complex tool selection.

  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% with a single parameter (pno) labeled '專案編號' (project number). The description does not add new meaning beyond the schema, but since coverage is high and the parameter is straightforward, a baseline of 3 is appropriate.

  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 retrieves a project's sprint list ('查詢專案的迭代清單'), using a specific verb+resource combination. It distinguishes from siblings like list_projects and list_requirements by specifying the entity ('sprints'), but could be more explicit about the resource type to improve 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. Given siblings like create_project and list_todos, the agent needs context on the tool's role in project management workflows, but none is provided beyond the basic purpose.

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

• list_todosC
  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 must fully disclose behavior. It only implies a read operation via '查詢' but does not explicitly state it is read-only, what happens on invalid project numbers, whether pagination exists, or any side effects. The mention of '包含欄位與項目' hints at output structure but lacks clarity.

  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?

  Single sentence containing essential purpose and scope. No redundancy. However, it could be expanded slightly to include usage context without losing conciseness.

  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 simple listing tool without output schema or annotations, the description lacks crucial context: return value structure, read-only nature, error behavior, and relationship to other todo tools. The hint about 'fields and items' is insufficient to fully understand what the agent will receive.

  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% (pno described as '專案編號'), so baseline is 3. The tool description adds no extra meaning beyond the schema—does not explain format, length, or examples. This is adequate but not additive.

  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 queries a project's to-do board including fields and items (查詢專案的待辦看板（含欄位與項目）). This distinguishes it from sibling list tools (e.g., list_projects, list_bugs) by specifying the resource type and inclusion of board structure.

  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 (e.g., create_todo, search_tags). No prerequisites mentioned (e.g., project must exist) and no scenarios where it should not be used.

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

• search_tagsC
  2.9/5.0
  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 for behavioral disclosure. It only states the action ('search') without disclosing whether the operation is read-only, what the response looks like, or any side effects or permissions. This is a minimal, non-informative disclosure beyond the tool's name.

  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, compact sentence with no filler or redundant information. Every word contributes to stating the purpose, making it appropriately concise and front-loaded.

  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?

  Despite the tool's simplicity, the description is incomplete for an AI agent. It lacks information about the return format (e.g., list of tag names, exact matches vs. partial), any filtering behavior, or how the keyword interacts with the project. With no output schema and no annotations, the description should provide this context.

  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 provides descriptions for both parameters ('pno' as project number, 'keyword' as search keyword), giving 100% coverage. The description adds no additional parameter meaning or context beyond this, so the baseline score of 3 is appropriate.

  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 clear verb ('搜尋' / search) and resource ('專案標籤' / project tags), making the primary action understandable. However, it does not explicitly mention the project scope (e.g., 'search tags within a project'), which is implied by the required 'pno' parameter, so it falls short of fully distinguishing usage from other list/create tools.

  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?

  There is no guidance on when to use this tool versus alternatives. The description is a simple statement without any 'use this when...' or 'instead of...' context, leaving the agent to infer suitability from the schema and sibling tool names.

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

• create_todoB
  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. It discloses that it is a 'write operation' and 'protected by whitelist and frequency limit', but does not explain what happens on success or failure, whether it is idempotent, what the response looks like, or any side effects. For a mutation tool this is insufficient.

  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 a single sentence with a parenthetical note, which is concise and front-loaded. It wastes no words, though it could be slightly more structured (e.g., separate usage from behavior).

  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 6 parameters (2 required), no output schema, and no annotations, the description is too brief. It does not explain return values, error handling, or any constraints beyond the protection note. For a tool with multiple parameters, this is incomplete.

  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 does not add any parameter-level meaning beyond the schema's own property descriptions. It mentions the project scope but does not elaborate on parameters like pno, title, or optional fields.

  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 ('建立' = create), the resource ('待辦項目' = to-do item), and the scope ('在指定專案中' = in a specified project). It also mentions it's a write operation with protections, which helps distinguish it from sibling tools like list_todos (read-only) or create_bug (different resource).

  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 like create_requirement or create_bug. There is no explicit mention of context, prerequisites, or when not to use it. The description only states what it does, not when to invoke it.

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

• list_projectsB
  3.1/5.0
  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. It only states that the tool lists projects, but does not specify whether results are paginated, sorted, filtered, or what permissions are required. Critical behavioral traits about return format or data limits are absent.

  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 a single concise sentence with no wasted words. However, it omits useful details that could be added without sacrificing conciseness, such as noting that it returns project names or IDs.

  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 zero parameters, no output schema, and no annotations, the description is the sole source of context. It adequately states the core functionality but lacks detail on return format, error behavior, or how the list is ordered or filtered. For a simple list tool, this is minimally adequate but leaves gaps.

  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 and 100% schema coverage, so the description does not need to clarify them. The description adds value by specifying that the list includes only 'accessible to the user,' which is meaningful context beyond the empty schema. Baseline 4 for zero-parameter tools is appropriate here.

  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 it lists projects accessible to the user, providing a specific verb and resource. It distinguishes from sibling tools like get_project_detail and list_sprints by resource, but does not explicitly differentiate from other list tools (e.g., list_requirements) beyond resource type.

  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 given on when to use this tool versus alternatives such as get_project_detail or list_requirements. There is no mention of prerequisites, exclusions, or context-dependent usage, leaving the agent to infer appropriateness.

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

• list_requirementsB
  3.1/5.0
  Behavior2/5

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

  No annotations exist, so the description must convey behavioral traits. It does not state that the operation is read-only, whether it supports fuzzy search (the keyword description hints at title fuzzy search but is not in the description), or what happens when no results are found. The parameter 'keyword' mention in schema is not echoed in the description, missing an opportunity to disclose search behavior.

  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 in Chinese that communicates the tool's purpose without extraneous text. It is front-loaded with the action and object, and every character earns its place. No fluff or redundancy.

  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 4 parameters, 100% schema coverage, no output schema, and no annotations, the description is minimally adequate. It does not explain return format (e.g., list of requirement objects, count) or edge cases (e.g., invalid project number). A moderately complete description would still need to mention search behavior and pagination effects, which are absent.

  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 baseline is 3. The description adds no information beyond the schema—it does not explain how parameters interact (e.g., keyword applies to title only, pagination with page/limit). However, since the schema already fully documents each parameter, the description does not detract but adds no extra semantic value.

  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 '查詢' (query) and the resource '需求清單' (requirements list), and distinguishes it from siblings like 'create_requirement' and 'get_requirement_detail' by framing it as a list operation. However, it does not explicitly mention that it lists requirements for a given project, though the parameter 'pno' implies this. The purpose is clear but could be more explicit about the resource being 'requirements of a project.'

  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, the difference from 'get_requirement_detail' (which likely returns a single requirement) or 'list_projects' (which lists projects) is not clarified. There is no mention of prerequisites or context such as needing a valid project number first.

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

• update_bugB
  3.1/5.0
  Behavior3/5

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

  Since no annotations are provided, the description carries the full burden. It correctly identifies the operation as a write (update) and mentions protection mechanisms (whitelist, rate limiting). However, it does not disclose what happens if the bug does not exist, whether partial updates are allowed, what the response contains, or any side effects like notifications. The behavioral disclosure is incomplete 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 very concise (one sentence) and front-loads essential information: the action, the object, and security constraints. It earns its place. However, it could be slightly improved by adding a brief note about parameter usage or prerequisites without becoming verbose.

  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 has 7 parameters, no output schema, and no annotations, the description is insufficient. It doesn't explain the return value (e.g., what happens on success), how to handle errors, or whether all fields are updated simultaneously. The description covers only the high-level purpose and protection, leaving the agent without guidance on parameter constraints or expected behavior after invocation.

  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 100%, so all 7 parameters have descriptions in the schema. However, the tool description itself does not add any meaning beyond what the schema already provides—it simply repeats '更新缺陷欄位' (update bug fields). It does not explain relationships between parameters (e.g., whether fields are optional or applied atomically) or provide usage context like formatting expectations for 'priority' beyond what's in the schema. With high schema coverage, a baseline of 3 is appropriate, but the lack of added value and the omission of any help for the 5 optional parameters that might be confusing (e.g., 'describe' is ambiguous between description and a verb) justifies a lower score.

  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 (update bug fields), the object (bug), and classifies it as a write operation. However, it lacks explicit differentiation from sibling tools like 'update_requirement' or 'create_bug', which is why it doesn't reach a perfect 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 mentions it is protected by a whitelist and frequency limit, implying constraints on when it can be used, but it does not specify when to use this tool vs. alternatives (e.g., create_bug for new bugs, or list_bugs to find the bug first). No guidance on prerequisites or exclusion criteria is given.

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

• get_requirement_detailB
  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. It only states it retrieves information without mentioning side effects, authentication needs, rate limits, or idempotency. The agent cannot infer whether this is a safe read operation or whether it has any constraints.

  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 a single, concise sentence with no wasted words. It is front-loaded with the core action, though it could be slightly expanded without becoming verbose.

  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 (two parameters, no nested objects, no output schema), the description is minimally adequate. It states the purpose but does not describe the return format or provide examples, which would be helpful for complete agent understanding.

  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% (both parameters have Chinese descriptions). The tool description adds no additional meaning beyond the schema, so the baseline score of 3 applies. The description does not explain parameter relationships or usage nuances.

  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 '取得單筆需求的完整資訊' (get complete information of a single requirement) clearly states the verb (get) and resource (requirement detail). The word '單筆' (single) distinguishes it from sibling tools like list_requirements, which retrieve multiple items.

  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 such as list_requirements or get_project_detail. It does not mention prerequisites, exclusions, or contextual triggers for selection.

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

• list_project_membersB
  3.2/5.0
  Behavior2/5

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

  With no annotations, the description should disclose behavioral traits such as required permissions, rate limits, or side effects. The text only states the tool's function, leaving the agent uninformed about authentication, data scope, or potential limitations.

  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 a single, efficient sentence that conveys the core purpose. It is front-loaded and concise, but could include more useful information without becoming verbose.

  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 low complexity (1 param, no output schema), the description minimally covers the tool's purpose. However, it lacks details about what the output contains (e.g., member names, roles) and any implicit constraints, making it adequate but not complete.

  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% (single parameter 'pno' with description). The description adds no extra meaning beyond the schema, so it meets the baseline of 3 for high coverage without adding value.

  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 '查詢專案成員' clearly means 'list project members', conveying a specific verb and resource. It distinguishes from sibling tools like list_projects and get_project_detail by indicating it returns members of a project, not the project itself.

  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 (e.g., get_project_detail might also include members). There are no prerequisites, exclusions, or contextual hints about when listing members is appropriate.

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

• update_requirementB
  3.2/5.0
  Behavior3/5

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

  The description discloses that this is a write operation (寫入操作) and warns about whitelist and frequency restrictions, which are helpful behavioral traits. Since annotations are absent, the description carries the full burden, and it provides adequate but not rich details—e.g., no mention of side effects, error conditions, or whether updates are atomic.

  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 a single, concise sentence that conveys the essential information without waste. It could be slightly more structured by front-loading the key verb, but it is efficient and to the point.

  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 complexity of 8 parameters and no output schema, the description provides basic context (write operation with restrictions) but lacks critical details such as return behavior, what happens on partial updates, or error handling. It is minimally adequate for an agent but leaves gaps in understanding the tool's full behavior.

  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 all 8 parameters. The description adds no additional meaning beyond what the parameter descriptions provide (e.g., it doesn't explain how fields interact or which are required for an update). Baseline 3 is appropriate since 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 action is to update requirement fields, which is a specific verb+resource combination. It distinguishes itself from siblings like create_requirement (creation) and get_requirement_detail (read-only). However, it doesn't explicitly differentiate from update_bug, which is a similar mutation tool.

  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 includes a vague note about protection (whitelist and frequency limits) but provides no guidance on when to use this tool versus alternatives like create_requirement for creating records or get_requirement_detail for reading. There is no explicit statement of prerequisites or conditions for calling this tool.

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

• create_projectA
  3.6/5.0
  Behavior3/5

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

  Since no annotations are provided, the description carries the full burden of behavioral disclosure. The description mentions it is a write operation ('寫入操作') and is protected by rate limits ('受頻率限制保護'), which adds transparency beyond what the schema provides. However, it does not disclose other behavioral traits such as overlapping project names, ownership, or response details.

  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 extremely concise at one line, with no wasted words. It front-loades the core purpose and includes key behavioral notes. It could be considered slightly under-specified for a creation tool, but it earns a 4 for being efficient and to the point.

  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 are only 2 parameters, no output schema, and no annotations, the description covers the basic fact that this is a write operation with rate limits. However, it lacks information about what happens after creation, whether duplicate names are allowed, and how the response looks. It is adequate for a simple project creation tool but could provide more context.

  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 baseline is 3. The description itself does not list or explain any parameters; it relies entirely on the schema. The description adds no additional meaning beyond what the input schema already provides for the 'name' and 'type' fields.

  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 '建立新專案' (create new project), which is a specific verb+resource combination. It distinguishes itself from sibling tools like 'list_projects' and 'get_project_detail' that are read-only, and from other creation tools like 'create_requirement', 'create_bug', and 'create_todo' that create different resource types.

  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 does not explicitly state when to use this tool versus alternatives. While it is clear from the name and description that one should use this to create a project, there are no usage guidelines for scenarios like when to use 'create_project' vs 'create_requirement' or what prerequisites exist. The description provides no exclusions or alternative suggestions.

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

• create_requirementA
  3.6/5.0
  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 it's a write operation with whitelist and rate-limit protection, but lacks details on return behavior, error states, or idempotency.

  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, front-loaded sentence that conveys the core action and key constraints without wasted 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?

  Given 6 parameters, no output schema, and no annotations, the description is too brief. It omits return format, error handling, and guidance on required parameters like pno.

  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 baseline is 3. The description adds no additional meaning beyond the schema; no parameter guidance or clarifications are provided.

  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 creates a requirement in a specified project, using a specific verb and resource. It distinguishes from sibling tools like update_requirement, get_requirement_detail, and create_bug.

  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 when to use (creating a new requirement in a project) but does not explicitly contrast with alternatives like update_requirement or include exclusions or prerequisites.

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

• create_bugA
  3.9/5.0
  Behavior4/5

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

  The description explicitly notes this is a write operation protected by whitelist and frequency limits, which adds valuable behavioral context beyond what the schema provides. Since no annotations are present, the description carries the full burden and does so effectively for the key concerns.

  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 a single sentence with a parenthetical, which is concise and front-loaded. No wasted words, but it could be structured more clearly, e.g., separating the behavioral note from the main purpose.

  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 creation tool with 5 parameters and no output schema, the description sufficiently covers purpose and key behavioral constraints. It does not explain return values or the relationship between project and bug, but these are not critical for a create operation.

  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 provides clear parameter meanings. The tool description adds no additional parameter-level details, resulting in no extra value beyond the baseline set by the 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 creates a bug in a specified project, using a specific verb and resource. This distinguishes it from sibling tools like create_project, create_requirement, and create_todo, which have different resources.

  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?

  No explicit guidance on when to use this tool versus alternatives. The description only states what it does, leaving the agent to infer usage context from the tool name and siblings. No when-not scenarios or alternative tool references are provided.

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