Server Quality Checklist

Tool Scores

• extractA
  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 full burden. It discloses that the server makes no outbound requests and that url is only for absolutizing links. However, it does not mention failure modes, performance traits, or safety (e.g., no destructive actions). The description is adequate but could be more explicit about behavioral expectations.

  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 sentences that immediately convey purpose, input constraints, and practical usage. No wasted words, front-loaded with key 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?

  Given the tool's complexity (18 parameters, nested objects) and presence of an output schema, the description is sufficiently complete for an agent to understand when and how to use it. It covers the core purpose and input preparation. Could mention that it uses Readability under the hood, but not necessary.

  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 100%, so baseline is 3. The description adds value by explaining the overall usage (e.g., 'Hand it the output of ...' for html parameter) and reinforcing constraints. This goes beyond the schema descriptions, justifying a higher score.

  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 extracts the main article from rendered HTML and returns clean Markdown plus metadata. It specifies the verb 'extract', the resource 'main article', and output format. It also distinguishes from siblings like html_to_markdown by focusing on article extraction, not arbitrary conversion.

  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 gives clear context: use when you have post-JavaScript HTML from browser devtools, and the server fetches nothing. It provides guidance on how to prepare input (use document.documentElement.outerHTML). However, it does not explicitly state when NOT to use or contrast with siblings beyond implicit differentiation.

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

• html_to_markdownA
  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 full burden. It mentions using the same Turndown + DOMPurify path as `extract`, implying sanitization, but does not disclose any potential side effects, error behavior, or edge cases. Adequate but minimal.

  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 sentences, both front-loaded with the core differentiator (no Readability) and usage context. Every word earns its place; no fluff.

  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 13 parameters, an output schema, and sibling tools, the description is brief but hits the critical distinction. It explains the input constraints and the relationship to `extract`. Some edge cases (e.g., format handling, error scenarios) are left implicit, but output schema covers return structure. Adequate for the complexity.

  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 baseline is 3. The description adds modest value by clarifying that `url` is only for absolutizing relative links and that the server does not fetch it, which reinforces the 'no fetch' behavior. No other parameter details beyond 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 converts HTML fragments to Markdown without Readability extraction, and explicitly distinguishes it from the sibling tool `extract` by specifying the use case (already isolated snippet).

  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?

  The description explicitly tells when to use (snippet isolated via chrome-devtools) and when not to (no Readability article extraction), and directly references the sibling tool `extract` as the alternative. The 'server fetches nothing' line further clarifies input constraints.

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

• outlineA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description fully discloses key behaviors: the server never fetches any external resources, 'html' is the sole data source, and 'url' is only used for origin context and absolutizing links. It also notes the absence of transformations like Readability or Turndown. This provides a comprehensive behavioral picture.

  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 sentences that front-load the purpose and then quickly detail behavioral constraints. No superfluous words; every sentence adds unique value. The structure is efficient and easy to parse.

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

  Completeness5/5

  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, 1 required, output schema present), the description covers all necessary aspects: purpose, usage context, behavioral traits, parameter roles, and relationship to siblings. It is fully sufficient for an AI agent to select and invoke the tool 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?

  The input schema covers both parameters with descriptions (100% coverage), meeting the baseline of 3. The description adds significant context beyond the schema: 'url' is 'NEVER fetched — origin context only', and 'html' is already-rendered and used unmodified. This additional semantic clarity justifies a score of 4.

  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: returning a document outline (h1-h6 headings with stable anchor ids) from already-rendered HTML. It distinguishes itself from siblings by emphasizing it is a 'pure heading walk' with no Readability, Turndown, or sanitization, making the purpose specific and non-ambiguous.

  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 positions the tool as a 'cheap pre-check before full extraction', implying it should be used when only headings are needed. It contrasts with extraction tools by listing what it omits (Readability, Turndown, sanitization). However, it does not explicitly name sibling tools or state when not to use it, but the context is clear enough.

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