Server Quality Checklist

Tool Scores

• list_providersA
  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. 'List' implies a read-only operation, and the description adds useful context about scope ('configured', 'BYOK') and returned content. However, it does not disclose potential behaviors such as whether it only returns built-in providers, if it can be empty, or whether any configuration is required first.

  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, front-loaded sentence that conveys the action, the subject, and the output contents without filler. Every word adds value.

  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 zero-parameter listing tool with no output schema, the description adequately conveys the purpose and the returned categories. It does not explain the BYOK acronym or give examples of capabilities, but those are minor omissions for such a simple 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?

  There are zero parameters, so the description does not need to explain parameter behavior. The baseline for no-parameter tools is 4, and nothing in the schema requires additional clarification.

  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?

  States a specific action 'List' with a clear resource 'configured BYOK generation providers' and explicitly names what is returned: 'their models and capabilities'. It is easily distinguished from sibling render_image and render_video, which perform generation rather than listing providers.

  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 this is a discovery/list operation used to inspect available generation providers, especially before rendering tasks. However, it does not explicitly state when to use this tool versus alternatives or exclude cases, though the sibling names make the distinction reasonably clear.

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

• render_imageA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It discloses the important side effect that output is written to disk, restricts input to self-authored markup, and sets expectations with 'Not photorealistic.' It does not describe overwrite behavior or return values, but the essential operational 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 two sentences with no wasted words. It front-loads the primary action and resource, then provides use cases and a limitation in a tightly packed second sentence.

  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?

  For a 6-parameter tool with no annotations and no output schema, the description plus schema is mostly sufficient: an agent can call it with just source and rely on defaults. However, it does not clarify what happens after rendering (returned file path? generated filename?) and does not mention how width/height or output_format influence the result, leaving some uncertainty.

  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 only 33%, so the description needed to compensate for width, height, format, and output_format. It usefully connects source content to the format enum ('SVG markup' vs 'full HTML document'), but does not explain output_format, filename, or dimension semantics beyond what the schema already provides.

  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 concrete verb ('Render'), names the accepted source types ('SVG markup or a full HTML document'), and states the output ('image file on disk'). It clearly distinguishes itself from siblings like render_video and list_providers, and adds a boundary with 'Not photorealistic.'

  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?

  It explicitly lists intended use cases: illustrations, diagrams, charts, UI mockups, typographic cards. It also provides an exclusion with 'Not photorealistic,' but it does not explicitly contrast with render_video or list_providers, so an agent is left to infer the alternative use cases.

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

• render_videoA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral disclosure burden. It does this well by specifying that draw(ctx, t, frame) must be deterministic, forbidding requestAnimationFrame and Date.now, noting optional setup(ctx) runs once, and stating the output is a file path plus sample frames. It does not cover render time, failure modes, or resource implications, leaving some behavioral gaps.

  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?

  Every sentence earns its place: purpose, function contract, optional setup, use cases, and return value. The most important constraint (pure deterministic draw function) is front-loaded, and there is no filler or repetition of schma details.

  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 an agent enough to call the tool correctly: the code contract, deterministic requirement, optional setup, and output shape. Minor gaps exist around duration_seconds semantics and more detailed return format, but the schema supplies defaults and the description covers the core complexity of code execution.

  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 low, so the description compensates by adding crucial semantics for the required draw_code parameter: the draw function signature, time in seconds, purity requirement, and optional setup(ctx). It does not explain duration_seconds or the dimension/fps parameters, but these are self-explanatory and have defaults in 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?

  The description opens with a specific verb and resource: 'Render an MP4 from JavaScript canvas animation code you author.' It clearly differentiates from render_image (static image) and list_providers (provider listing), and reinforces the video/animation scope with 'Use for motion graphics, animated diagrams, explainers.'

  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?

  Clear use-case guidance is given ('Use for motion graphics, animated diagrams, explainers'), which implies when render_video is appropriate. However, it does not explicitly name alternative tools or state when not to use it, such as 'for static images use render_image instead.'

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