Server Quality Checklist

Tool Scores

• take_screenshotA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It adds useful details like 'Returns the public image URL (24h TTL) and metadata', but it does not explain what happens on failure, rate limits, authentication requirements, or how rendering works. This is partial transparency, not comprehensive.

  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 compact sentences with no filler. The core action and deliverable are front-loaded, followed by a useful usage tip. Every clause 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?

  The description gives essential output context (public URL, 24h TTL, metadata) and the schema fully documents parameters. It is not a 5 because there is no output schema and the description does not cover error cases or operational constraints like network reachability or rendering behavior.

  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% description coverage for all parameters, so the schema already explains url, delay, format, blockAds, fullSize, resolution, and blockCookiesGdpr. The description only reinforces fullSize and the format list, adding no new parameter-level meaning beyond the schema. 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 uses a specific verb ('Capture'), names the resource ('a PNG/JPEG/PDF screenshot of any public URL'), and mentions the service ('WebsiteScreenshot.online'). This clearly differentiates it from sibling tools like record_website_video and check_video_status, which are about video capture/status rather than static screenshots.

  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 a usage hint ('Use fullSize=true for full-page captures') and constrains to public URLs, but it does not explicitly state when to choose this tool over record_website_video or check_video_status, nor does it mention exclusions. Usage is implied rather than directly compared with alternatives.

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

• check_video_statusA
  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 this is a polling operation on status, implying a non-destructive read. But it does not describe what the response looks like (e.g., possible statuses like pending/completed/failed), nor does it mention any polling cadence or eventual termination. The description is safe but minimal, lacking deeper behavioral context like potential errors or rate limits.

  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?

  A single, focused sentence that front-loads the action and the source of the input. There is no extraneous wording; every part earns its place, making it easy to scan and understand.

  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 polling tool with one well-documented parameter and no output schema, the description adequately covers what the tool does and where the requestId originates. It could mention that polling is repeated until a terminal status is reached, but this is a minor gap given the minimal 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?

  The schema provides full coverage (100%) and the requestId parameter has an explicit description stating it comes from record_website_video with async=true. The tool description adds no additional meaning beyond that, so baseline 3 applies. The schema already handles parameter semantics effectively.

  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 a specific verb ('poll'), the target resource ('status of an async video job'), and ties it explicitly to the creating tool, record_website_video with async=true. It distinguishes itself from siblings by stating its specific role in the async workflow, so an agent can easily identify its purpose.

  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 implies when to use it: after calling record_website_video with async=true and receiving a requestId. It gives context on where the requestId comes from. However, it does not explicitly state when not to use it (e.g., for sync jobs) or mention alternatives. Still, the context is clear enough for basic usage.

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

• record_website_videoA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses key behaviors: returns a public video URL with 24h TTL and supports async polling. It implicitly indicates that sync mode returns the video URL directly, implying it waits for completion. It does not mention failure modes or rate limits, but it covers essential outcome and async flow.

  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 fluff. The first states purpose and output; the second explains async usage. It is front-loaded and efficient.

  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?

  While the tool has many parameters, the schema covers their specifics. The description mentions the async workflow and TTL, and references check_video_status. It does not mention limitations like recording duration or errors, nor guidance on when to use this vs take_screenshot, but the essential usage is covered with the schema.

  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 73%, so the schema already documents most parameters. The description adds meaningful guidance for the async parameter: 'Pass async=true to receive a requestId; poll check_video_status until status=completed or status=error,' which explains the workflow and connection to the polling tool. It also clarifies that the URL must be public, aiding interpretation of the url 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 action: 'Record a scrolling webm/mp4/gif capture of any public URL.' It distinguishes from the sibling take_screenshot by emphasizing 'scrolling' and 'video capture' with format options. It also mentions the output URL with TTL, providing a specific verb+resource.

  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 explicit guidance for async mode: 'Pass async=true to receive a requestId; poll check_video_status until status=completed or status=error.' It references the sibling check_video_status and explains the workflow. However, it does not explicitly contrast with take_screenshot or state when to prefer this tool over a screenshot, so it lacks a full when/when-not directive.

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