Server Quality Checklist

Tool Scores

• run_visual_testB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description must fully disclose behavioral traits. It states that the tool uses a 'real browser' (a nontrivial resource implication) and returns a pass/fail report, but it omits key details such as whether the tool is read-only, any potential side effects (e.g., network requests to the target URL), error handling (e.g., invalid URL), or timeouts. This is insufficient for an agent to predict execution consequences.

  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 with no redundant words. The first sentence front-loads the core action and scope, and the second enumerates check types and the output. Every element contributes directly to understanding the tool—no filler or filler phrases. It is exemplary in efficiency.

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

  Completeness2/5

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

  Given there is no output schema or annotations, the description must fully equip an agent to call the tool. It fails to specify the exact format of the 'checks' array (e.g., that each check needs both type and value), and the promised 'detailed pass/fail report' is not described in terms of structure or fields. The tool's complexity (nested object array, four distinct check types) demands more explicit guidance than provided.

  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 0%, so the description must compensate. It adds meaning to the 'checks' parameter by explaining each enum value ('has_text', 'has_element', etc.), which the schema only lists mechanically. However, it does not explain the structure of the checks array (each item requires a 'type' and a 'value'), nor does it clarify that the 'url' parameter should be a valid URI or how the value field is used per check. Thus it partially compensates but leaves structural ambiguity.

  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: running visual checks against a URL using a real browser. It enumerates the four supported check types with brief explanations, which precisely defines the resource and scope. This distinguishes it from sibling tools (take_screenshot, scrape_page) which focus on capture rather than validation, even though siblings aren't explicitly named.

  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 this tool (when you need to verify page content via checks) but does not explicitly contrast it with alternatives like take_screenshot or scrape_page. It provides no guidance on when NOT to use it or conditions that would favor a sibling tool. The usage context is clear from the purpose but lacks explicit routing.

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

• scrape_pageA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It discloses that it uses a 'real browser,' truncates body text to 'first 5000 chars,' caps links at 'up to 30,' and optionally uses a CSS selector for specific content. These limitations are explicit and useful. However, it does not mention error handling, wait times, or bot detection implications, which could be relevant but are not strictly necessary for basic use.

  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 front-loaded with the primary action and output, followed by the optional selector. Every sentence contributes value, and there is no redundant phrasing. It wastes no words and is easy 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?

  For a relatively simple scraping tool, the description covers the essential inputs, the extraction behavior, and the return content. It does not have an output schema, but the description enumerates what is returned. It omits non-critical details like timeout behavior or concurrency limits, but for most use cases the information is sufficient. Slightly more context on when to use it would push this to 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?

  Schema description coverage is 0%, so the description must clarify the parameters. It explains 'url' as the target to navigate and defines 'selector' as 'a CSS selector to extract a specific element's text.' This adds meaningful semantics beyond the raw schema types (string, string). It does not fully detail edge cases (e.g., invalid selector), but the core usage is clearly communicated.

  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 clear purpose: 'Navigates to a URL with a real browser and extracts structured content.' It lists the exact content items (title, meta description, body text, links) and the optional selector capability. This distinguishes it from the sibling tools take_screenshot and run_visual_test, which are visual in nature.

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

  Usage Guidelines2/5

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

  The description provides no explicit guidance on when to use this tool versus the sibling tools (take_screenshot, run_visual_test). It does not mention when not to use it, what alternatives exist, or any prerequisites like needing to scroll or handle dynamic content. The usage is only implied by the description of the extraction behavior, not stated.

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

• take_screenshotA
  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. It discloses that it uses a real headless browser and that the return value is a base64 string, and it explains the fullPage behavior. This is adequate transparency for a simple screenshot tool, though it does not mention potential limitations like timeouts or access restrictions.

  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 with no filler. The primary action and output format are front-loaded, and the optional parameter guidance follows logically. Every word contributes meaning.

  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 tool of this simplicity (two parameters, no output schema), the description is largely complete. It covers the return format, the fullPage option, and the general behavior. Minor omissions like error conditions or access requirements are not critical for an agent to invoke 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 0%, so the description must compensate. It explains the fullPage parameter ('capture the entire scrollable page') but does not add detail about the 'url' parameter beyond what is obvious from the description ('any URL'). Since url is self-evident and fullPage is clarified, the description adds moderate value but does not fully cover both parameters.

  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 clear verb ('Captures'), a specific resource ('PNG screenshot of any URL'), and the return type ('base64-encoded string'). It is immediately distinct from the sibling tools (scrape_page, run_visual_test) by its explicit focus on capturing a page image.

  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 clear context for what the tool does and introduces the fullPage option, but it does not explicitly compare against sibling tools or state when not to use it. The usage is implied — if you need a screenshot, use this — but no alternatives or exclusions are given.

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