Server Quality Checklist

Tool Scores

• search_stockB
  3.4/5.0
  Behavior2/5

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

  No annotations were provided, so the description carries the full burden of behavioral disclosure. It merely states the search action and returned data without revealing any additional traits such as fuzzy matching behavior, handling of ambiguous matches, sort order, or the fact that the operation is read-only. For a search tool this is a modest but notable 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 a single, dense sentence in Chinese that immediately conveys the core function and output. There is no filler or redundant repetition of parameter names. It earns its place entirely.

  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 simple two-parameter search tool, the description covers the essential inputs and outputs (returned code and market). However, with no output schema and no annotations, the description doesn't fully specify the exact return format, possible empty-result behavior, or the effect of the limit parameter in practice. It is adequate for basic invocation but leaves some contextual 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?

  The schema already documents both parameters well (coverage 100%). The description adds value by specifying that 'keyword' can be a name, pinyin, or code fragment, which goes beyond the schema's examples ('茅台', '腾讯', 'apple'). This extra semantic nuance helps the agent understand the acceptable input range for the keyword 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's function: searching stocks by name, pinyin, or code fragment, and returning the stock code and market. The verb 'search' plus the resource 'stocks' is specific, and the supported search modes add useful detail. Although it doesn't explicitly differentiate from the sibling 'get_stock_quote', the naming and described output make the distinction obvious enough.

  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 the tool: when you need to find a stock code or market by a keyword like a name or code fragment. However, it offers no explicit guidance on when not to use it, nor does it mention that get_stock_quote is the appropriate sibling for retrieving price data. The examples in the schema hint at typical usage but don't formally establish selection criteria.

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

• get_current_weatherA
  4/5.0
  Behavior3/5

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

  无注解信息，描述自行说明了数据源为 Open-Meteo 且无需 API key，填补了认证和来源信息。但未说明城市不存在时的行为、数据时效性、异常处理或响应格式，行为披露仍不完整。

  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?

  单句描述，信息密度高，先说明核心功能，再列返回要素、数据源和鉴权要求，没有冗余内容。

  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?

  对于只有一个参数且无输出 schema 的简单查询工具，描述已覆盖返回内容、数据源和鉴权要求，足以让代理理解如何调用。缺少输出结构示例和失败语义，但尚不构成严重缺口。

  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?

  参数 schema 覆盖率为 100%，city 参数的中英文示例和最小长度已足够。描述未额外补充参数格式或约束，因此维持基线 3。

  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?

  描述明确使用动词“查询”和资源“指定城市的当前天气”，并列出返回的具体要素（温度、湿度、天气现象、风速），与股票、RSS、文件字数等兄弟工具完全区分。

  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?

  描述清楚说明该工具用于获取指定城市的实时天气，使用场景明确；同列兄弟工具均属其他领域，无需额外排除说明。但未显式提及“需要天气信息时使用”或何时不使用。

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

• read_rss_feedA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that the operation is a read and lists the returned fields, but does not mention network fetching behavior, error handling, caching, or what happens with invalid feeds. Basic behavior is covered, but edge cases are not.

  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 purpose and return fields without waste. Every word earns its place.

  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?

  Although there is no output schema, the description explicitly lists returned fields (title, link, publish time). The two parameters are fully documented in the schema, and the tool's simplicity means nothing critical is missing for an agent to call it correctly.

  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 does not add parameter-specific meaning beyond the schema, but the schema already documents both 'url' and 'limit' adequately.

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

  Purpose5/5

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

  The description states a specific verb ('read') and resource ('RSS/Atom feed'), and specifies what is returned (latest entries with title, link, publish time). This clearly distinguishes it from the unrelated sibling tools (stock quotes, weather, word counts).

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

  Usage Guidelines4/5

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

  The description clearly indicates the tool is for reading RSS/Atom feeds, so the use case is obvious. It does not explicitly mention alternatives or exclusions, but siblings are in different domains, so no such guidance is necessary.

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

• count_file_wordsA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses that the operation is a read-only count and restricts to plain text files. However, it does not clarify edge cases such as encoding handling, word definition conventions, or behavior on missing/unreadable files, which would make the behavior fully transparent.

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

  Conciseness5/5

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

  Two short Chinese sentences deliver all essential information with zero waste. The core function and the 'like wc' comparison appear first, and the plain-text constraint follows immediately. Perfectly front-loaded and concise.

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

  Completeness4/5

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

  For a simple, read-only counting tool, the description sufficiently explains what the tool does and its key constraint. Since there is no output schema, the agent might not know the exact return JSON structure, but the counts are named explicitly and 'like wc' gives a strong hint. Minor gaps around error handling and return format prevent a 5.

  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 schema covers 100% of the single parameter with a clear example. The description adds value beyond the schema by specifying the file must be local and plain text, constraining what kind of path is acceptable. This goes beyond the bare schema description.

  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 uses a specific verb (统计/count) and resource (本地文本文件的行数、词数和字符数), explicitly comparing to 'wc'. This makes the tool's function unmistakable and clearly distinct from unrelated siblings like stock quotes or weather.

  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 implies when to use the tool (when counting lines/words/characters of a text file) and includes an explicit limitation ('仅支持纯文本文件'), which warns against non-plain-text inputs. It does not name alternatives, but the sibling tools are so unrelated that no routing guidance is necessary.

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

• get_stock_quoteA
  4.5/5.0
  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 of behavioral disclosure. It does communicate real-time data, market coverage, batch capability, and flexible symbol formats, but it does not describe the return shape, error behavior, or data-source caveats. This is adequate but not rich.

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

  Conciseness5/5

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

  The description is compact and well-structured: it front-loads the core purpose, then gives market-specific format guidance, then closes with a fallback routing instruction. Every sentence earns its place with no filler.

  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 single-parameter quote tool, the description is nearly complete: it covers supported markets, code formats, batch behavior, limits in the schema, and the fallback to search_stock. The only notable gap is the lack of any description of the returned quote data, which matters because there is no output schema, but this does not prevent correct invocation.

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

  Parameters5/5

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

  Although the schema already documents the symbols array with 100% coverage, the description adds substantial meaning beyond the schema: exact symbol-format conventions for A-shares, HK stocks, and US tickers, plus the batch-query capability. This materially helps an agent construct valid inputs.

  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 retrieves real-time stock quotes for A-shares, HK, and US markets, and supports batch queries. It names the resource (stock quotes) and distinguishes itself from the sibling search_stock tool by being the quote-retrieval step after a code is known.

  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?

  It explicitly provides when to use this tool versus search_stock: if the user is unsure of the stock code, search_stock should be used first. It also gives concrete code-format examples for each market, making the appropriate call pattern clear.

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