Server Quality Checklist

Tool Scores

• scrape_single_noteA
  3.7/5.0
  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 mentions 'scrape and analyze' but does not describe key behaviors such as network requirements, rate limiting, authentication (e.g., login status), error handling (e.g., invalid URL, note not found), or what 'analyze' specifically does. Without these details, the agent may misuse the tool or encounter unexpected failures.

  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: two short sentences defining the purpose and context, followed by structured Args and Returns sections. Every sentence serves a clear function, and there is no redundancy. The format is easy to parse and front-loaded with the most critical information.

  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 (2 parameters, no annotations, has output schema), the description covers the essential purpose, parameters, and return format. However, it lacks important context about behavioral aspects (e.g., rate limits, login requirements, error scenarios) that would help an agent use it reliably. Completeness is adequate for straightforward use but not comprehensive.

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

  Parameters4/5

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

  The input schema has 0% description coverage, so the description is the sole source of parameter semantics. It provides meaning for both parameters: note_url is explained with an example URL, and max_comments is described as the maximum number of comments to scrape with a default of 100. This adds significant value beyond the schema's bare property titles. A slight deduction for not specifying format requirements (e.g., valid URL patterns) or edge-case behavior.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: scraping and analyzing comments from a single Xiaohongshu note given a URL. It uses specific verbs ('抓取', '分析') and specifies the resource ('单篇小红书笔记的评论'). The sibling tools (run_search_task, analyze_comments, check_login_status) are distinct, and the description explicitly frames the use case as '已知笔记URL、只需抓取单篇评论的场景', which differentiates it from search or bulk tasks.

  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 a clear usage context: when you have a known note URL and only need to scrape comments from that single note. However, it does not explicitly state when not to use this tool (e.g., for batch scraping or analysis without scraping), nor does it mention alternatives like run_search_task for searching notes or analyze_comments for analyzing already scraped data. The guidance is implied rather than overt.

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

• analyze_commentsA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the full burden. It states the tool reads a JSON file and returns JSON analysis results, implying it is read-only and does not modify the original file. However, it does not disclose any potential side effects, required permissions, or error handling (e.g., missing file). The behavioral traits are partially transparent but lack depth.

  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—three short sentences that cover the tool's purpose, usage scenario, and parameter. There is no wasted text, and the structure is front-loaded with the core action. Every sentence earns its place.

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

  Completeness3/5

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

  The description claims re-analysis with 'different parameters' but only exposes the file_path parameter, suggesting the analysis parameters are embedded in the file or tool configuration—this is unclear. The return type is mentioned but not detailed. Given the tool's simplicity, the description is moderately complete but leaves ambiguity about how analysis parameters are controlled.

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

  Parameters4/5

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

  The only parameter 'file_path' has a description in the tool description ('path to scraped comment JSON file') that adds meaning beyond the schema's title 'File Path'. The schema coverage is 0%, so the description compensates well. It could be more specific (e.g., absolute path, supported formats), but it is sufficient for the single parameter.

  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 re-analyzes scraped comment JSON files for keyword, sentiment, and popularity. It distinguishes from sibling tools (run_search_task, scrape_single_note, check_login_status) which are for different tasks. However, the exact nature of 'analysis' is not fully specified, leaving some ambiguity.

  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 says it is suitable for re-analyzing existing data with different parameters. This provides clear context for when to use it. It does not mention exclusions or alternatives, but no sibling tool directly competes for this re-analysis purpose.

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

• run_search_taskA
  3.9/5.0
  Behavior3/5

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

  描述公开了核心行为（搜索、抓取、分析、导出）和返回结果（JSON摘要和文件路径），但由于缺少annotation，其未说明是否需前置登录、文件写入的持久性/位置、速率限制或错误处理等副作用，整体透明度中等。

  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?

  描述以功能概述开头，后跟一行自动化流程，再按列表形式列出参数，结构清晰。但参数描述较详细，可适当精简，整体无冗余，信息密度合理。

  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?

  描述覆盖了核心操作和所有参数，但缺少对错误处理、前提条件（如登录状态）、输出模式的具体字段说明以及文件路径的显式描述，导致在复杂场景下代理可能无法完全预知调用后的完整结果。

  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?

  输入模式description coverage为0%，描述完全补偿了参数的语义缺失。为所有8个参数提供了清晰的定义、可选范围（如max_notes 1-200）、默认值和必填/可选标记，使代理能准确理解每个参数的作用。

  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?

  描述以“搜索小红书笔记并批量抓取产品评论”开头，明确说明了动词+资源，随后列出了详细的自动化流程（搜索、抓取、分析、导出），直接与兄弟工具（scrape_single_note）形成对比，清晰标识了工具的整体范围和输出。

  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?

  描述详细说明了参数用法（必填和可选），隐含了端到端批量任务场景，但没有明确说明何时应避免使用此工具（例如，只需抓取单条笔记时使用scrape_single_note），缺少与兄弟工具的显式区分指南。

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

• check_login_statusA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the key side effect of automatically opening a browser window for manual login if not logged in. It also mentions the return format. However, it does not clarify whether the tool blocks until login completes or times out, which is a minor gap.

  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 concise with three short sentences plus a return line. Every sentence serves a clear purpose: stating the function, describing the automatic behavior, and indicating the output format. No wasted words.

  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 has no parameters and an output schema exists, the description adequately covers the core functionality and side effect. It could be improved by explicitly linking to sibling tools as a prerequisite, but overall it provides sufficient context for an agent to understand when and how to use it.

  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 schema coverage is trivially 100%. The baseline is 4 per the rubric. The description does not add parameter-specific information but that is unnecessary. It provides context about the return value format, which is beneficial but not part of parameter semantics.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: checking Xiaohongshu login status and determining whether manual login is needed. It distinguishes itself from sibling tools like 'run_search_task' or 'scrape_single_note' by focusing on authentication rather than data operations.

  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 implies the tool should be used to verify login status before performing other tasks, and it explains the automated browser opening when not logged in. However, it does not explicitly state when to use this tool versus alternatives or mention prerequisites, leaving some implicit inference.

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