Server Quality Checklist

Tool Scores

• crawl_siteA
  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 states the tool returns structured JSON but does not mention side effects such as sending a large number of requests to the target site, potential rate limiting, execution time, or error handling. This lack of behavioral transparency beyond the basic action is a significant gap for a potentially heavy operation.

  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 two sentences that front-load the core action and result, and it includes a use case. Every word is purposeful, with no redundancy or filler.

  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 complexity (10 parameters, no output schema), the description provides the core purpose and a use case but lacks behavioral details like execution time, rate limits, and impact on the target site. The return format is described as structured JSON but not detailed; this is acceptable given the schema's parameter coverage, but the description does not fully compensate for the lack of annotations and output schema.

  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% coverage with descriptions for all 10 parameters, so the description does not need to repeat them. The description adds no additional parameter semantics beyond what the schema provides, meeting the baseline of 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?

  The description clearly states the tool runs a full site crawl with SiteOne Crawler and returns structured JSON with SEO, performance, and security metrics. This distinguishes it from sibling tools like crawl_single_page by emphasizing 'full' and 'comprehensive site audits.'

  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 'Use for comprehensive site audits,' which indicates when to choose this tool over alternatives like crawl_single_page. It does not explicitly name alternatives or exclusions, but the context is clear that this is for full-site audits rather than single-page checks.

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

• generate_sitemapA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry full behavioral transparency. It states it crawls and generates a sitemap, but does not disclose side effects (e.g., writing a file), rate limits, or whether it's safe/read-only. For a tool that creates a file, this is a 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 two sentences, front-loaded with the primary action and return value, followed by a clear use case. Every sentence earns its place; there is no waste or redundancy.

  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 3-parameter tool with no output schema, the description conveys the core function, return value, and use case. It is mostly complete, though it could add a note about whether the crawl is limited or has any side effects. Overall, it is adequate for basic usage.

  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 all 3 parameters with descriptions and defaults, so the description does not need to add parameter details. The description adds no extra meaning beyond the schema, matching the baseline of 3 for full schema coverage.

  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: 'Crawl a website and generate an XML sitemap file.' It also specifies the return value (file path and crawl summary), making it distinct from sibling tools like crawl_site which only crawl.

  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 provides a clear use case ('Use for SEO audits or submitting sitemaps to search engines'), giving context for when to use it. However, it does not explicitly mention alternatives or when not to use it, so it lacks exclusion guidance.

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

• crawl_single_pageA
  4/5.0
  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 tool returns JSON data and is 'fast and lightweight,' giving some behavioral context. However, it does not specify what the analysis includes, whether it performs any mutations, or potential edge cases (e.g., redirects, JavaScript rendering). This leaves gaps that annotations would normally fill.

  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 two sentences, front-loaded with the action and followed by a use case. Every word is purposeful, with no redundancy. It is concise and well-structured, making it easy for an agent to parse quickly.

  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?

  The tool is simple with 3 parameters and no output schema, so the description must convey the return expectation. It states that JSON data is returned but does not describe the JSON structure or any limitations. Given the context signals (siblings, rich schema), the description is largely complete but lacks details about the response contents, which prevents a 5.

  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% coverage, with descriptions for all three parameters: url, device, and extra_columns. The description adds no extra meaning beyond referring to 'the specified URL.' Since the schema fully documents the parameters, a baseline score of 3 is appropriate.

  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 'Analyze a single page with SiteOne Crawler' and specifies it 'Returns JSON data for just the specified URL.' This distinguishes it from sibling crawl_site by emphasizing single-page scope and the phrase 'quick page-level audits.' The verb 'analyze' and resource 'single page' are specific and unambiguous.

  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 says 'Fast and lightweight — use for quick page-level audits,' which provides a clear use case. It implicitly contrasts with crawl_site by focusing on a single page, but does not explicitly name alternative tools or state when not to use it. The sibling tool names are visible via context signals, so the guidance is adequate but not fully explicit.

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

• export_markdownA
  4/5.0
  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 the core action (crawl and export) and the return values (directory path and crawl summary). However, it omits behavioral details such as how the crawl handles page boundaries, link following, rate limits, or potential side effects, leaving a moderate transparency 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 at two sentences, front-loaded with the primary function and return values, followed by a compact list of use cases. Every sentence earns its place with no redundancy or 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?

  Given there is no output schema and no annotations, the description adequately covers the essential return information and intended use cases. However, it does not address edge cases like handling external links, file naming specifics, or the impact of max_depth on results, and it does not reference sibling tools for alternative scenarios, making it complete but not exhaustive.

  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 all three parameters (url, max_depth, output_dir) with descriptions, achieving 100% schema coverage. The description adds no parameter-specific semantics beyond the overall crawl-and-export behavior, 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.

  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 action: 'Crawl a website and export each page as a markdown file.' It uses a specific verb and resource, and also mentions the return values (export directory path and crawl summary), which distinguishes it from siblings like crawl_site or generate_sitemap that don't focus on markdown export.

  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 provides explicit use cases: 'Use for content migration, offline analysis, or feeding pages into other tools.' This gives clear context for when to use the tool. However, it does not explicitly contrast with sibling tools like crawl_site or mention when not to use it, so it lacks explicit exclusions or alternative references.

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

• get_crawl_summaryA
  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, but it only mentions the shallow crawl and returned statistics. It does not disclose potential side effects like network requests to the target site, rate limits, or any mutation risks, though the tool appears read-only. The description adds the 'shallow' behavioral trait, but more detail would be needed for a non-annotated tool.

  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 two sentences, the first directly states the tool's function and outputs, and the second gives usage guidance. It is front-loaded, efficient, and every sentence adds value with no redundancy.

  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?

  The description explains the high-level return values and health-check use case, which is sufficient for a relatively simple tool without an output schema. It covers purpose, usage, and resource scope, though it could detail error handling or exact output format more, but the essentials are present.

  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 three parameters (url, max_depth, rows_limit). The description adds no parameter-specific meaning beyond hinting at shallowness, which is already captured by max_depth's 'Shallow crawl depth'. Baseline 3 is appropriate.

  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 runs a quick, shallow crawl and returns high-level statistics such as status code distribution, response times, and error counts. This specific verb+resource+output distinguishes it from siblings like crawl_site or crawl_single_page, which imply more comprehensive crawling.

  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 positions the tool as 'best for fast site health checks before running a full crawl,' giving clear usage context. It implies a complement to full crawls but does not name alternative tools or provide explicit when-not-to-use scenarios beyond the full-crawl distinction.

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