Server Quality Checklist

Tool Scores

• fetch_web_mdA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It does disclose the return shape (page title + Markdown body), the preservation of structure, and the max_chars truncation. It does not mention error behavior, non-HTML responses, or other edge cases, but for a read-only fetch tool this is a reasonable but not thorough disclosure.

  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 front-loaded with the core action, uses a compact parameter/return structure, and contains no filler. Every sentence contributes to understanding what the tool does and what it returns.

  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 two-parameter fetch-and-convert tool, the description covers input, output, truncation, and recommended use case. The output schema further reduces the need to explain return values. It is slightly incomplete regarding explicit sibling routing and failure behavior, but overall sufficient.

  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 documents max_chars well, but url has no schema-level description. The tool description adds a concrete URL example for url and restates the meaning of max_chars, so it partially compensates for the 50% schema coverage. It does not add much depth beyond the example.

  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: '抓取一个网页并转换为 Markdown' and specifies what Markdown elements are preserved. It doesn't explicitly distinguish from the sibling fetch_web, but the Markdown-vs-plain-text framing makes the differentiation largely inferable.

  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 gives a clear intended use case: '比纯文本更适合喂给 LLM / 文档化场景'. However, it does not explicitly say when to prefer this over siblings like fetch_web or fetch_urls, nor does it state when not to use it.

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

• fetch_rssA
  4/5.0
  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 that the tool parses feeds and returns a plain-text article list with specific fields, which is useful. However, it does not mention error behavior, network timeouts, authentication needs, or the fact that malformed/non-feed URLs will be rejected.

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

  Conciseness5/5

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

  The description is compact and well-structured with separate sections for purpose, parameters, and return value. Every sentence provides useful information, and the most important operation is stated first.

  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?

  This is a simple tool with only two parameters, an output schema, and a clear return-value description. The description is sufficient for correct invocation. It could be more complete by mentioning that only valid RSS/Atom sources are supported, but this is largely implied and not a serious gap.

  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?

  Schema coverage is 50% because the 'url' parameter has no schema description. The description compensates by explaining the URL parameter and providing a concrete example URL. The 'limit' parameter is already documented in the schema with a range and default, so the description adds little beyond that.

  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 '解析' (parse) and names the exact resource (RSS/Atom feed), plus the returned fields. This clearly distinguishes it from generic web-fetching siblings like fetch_web and fetch_urls.

  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 it is for RSS/Atom feeds only, and the sibling names suggest alternatives, but there is no explicit statement of when to use fetch_rss versus fetch_web, fetch_web_md, or fetch_urls. The agent must infer the usage boundary from the resource type.

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

• fetch_urlsA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does disclose non-obvious behavior: partial-failure isolation ('单点失败不影响整体'), per-item failure reasons, and a 5-URL cap. It doesn't mention rate limits or content-type constraints, but the key operational traits are visible.

  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 well-structured: a one-line intent, a compact parameter list, and a clear return format. It front-loads the most critical behavioral trait (failure isolation) and avoids unnecessary 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 moderately simple tool with an output schema present, the description gives enough to invoke it correctly: input shape, size limit, output format, and failure behavior. The main gap is explicit differentiation from sibling tools, but that is not fatal to correct invocation.

  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?

  Schema covers mode and max_chars well, giving about 67% coverage. The description adds the important missing constraint for urls: a maximum of 5 URLs, which is not in the schema. It also clarifies the per-item character limit context.

  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 ('批量抓取多个网页') and the result (title + body summary per page). The batch/multiple-URL scope distinguishes it from single-page siblings like fetch_web, and the return contract is explicit.

  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 it should be used when fetching multiple URLs at once, but it never explicitly says when to choose it over fetch_web, fetch_web_md, search_web, or fetch_rss. No exclusions or alternative routing are provided.

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

• fetch_webA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It does well by revealing automatic noise removal, returning title + plain text, and the max_chars truncation behavior. It does not cover failure modes or rate limits, but for a simple fetch tool the core behavior is 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?

  The description is tightly structured with an action line, parameter list, and return section. Every sentence earns its place, and the most important behavioral detail (noise removal) is front-loaded. No filler or redundant explanation.

  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 2-parameter fetch tool with no annotations, the description covers input semantics, output shape, and preprocessing behavior. It could be slightly more complete by referencing alternatives or error behavior, but an agent has enough to invoke it correctly.

  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?

  Schema coverage is 50%: max_chars has a full description with range and default, but url is undocumented in the schema. The description compensates by defining url as a webpage address and providing an example, while restating max_chars meaning. This adds meaningful value beyond 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?

  Description clearly states the action: fetch a single webpage and extract clean body plain text, removing navigation/script/style noise. This distinguishes it from siblings like fetch_web_md (markdown output), fetch_urls (multiple URLs), search_web (search), and fetch_rss (RSS feed).

  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: when you need a webpage's readable body text for LLM consumption. However, it never explicitly compares against alternatives or states when not to use this tool, even though sibling tools are listed and the distinction would be valuable.

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

• search_webA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It explicitly discloses the backend (DuckDuckGo), lack of API key requirement, and the plain-text result format. This gives the agent a good understanding of what the tool does, though it does not mention potential rate limits or failure modes.

  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, with the core purpose stated first, followed by a clear parameter list and return format. No filler or redundant prose. Every sentence provides useful information.

  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 relatively simple search tool, the description covers the essential aspects: what it searches, how results are returned, and parameter meanings. The output schema covers the return structure, so the text description of return values is a helpful addition. It could mention behavior on no results or network errors, but these are minor gaps for a search tool.

  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 description provides meaning for the 'query' parameter, which is entirely undocumented in the schema, by calling it the search keyword. For 'max_results', it restates the schema's purpose but adds no new information. Since schema coverage is only 50%, the description compensates for the gap on the required parameter.

  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 function: search the web and return a list of titles, links, and summaries. This directly distinguishes it from sibling fetch_* tools, which are focused on retrieving specific URLs or RSS feeds. The mention of DuckDuckGo and no API key adds specificity.

  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 intended use is implied by the tool's name and description: use it when you need to search the web rather than fetch known URLs or feeds. However, the description does not explicitly state when to prefer this tool over siblings like fetch_web or fetch_rss, nor does it mention any exclusions or alternatives.

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