Server Quality Checklist

Tool Scores

• take_screenshotA
  4/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the full burden of behavioral disclosure. It mentions that the result is a PNG (though format is configurable) and lists supported capture modes, but it does not disclose potential limitations, error conditions, or the binary nature of the response. The description adds some value but leaves gaps typical of a simple screenshot 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 states the primary action and return type, the second lists the main capabilities. It is tightly written with no redundant information, and the most essential facts are front-loaded.

  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?

  With a rich 100%-covered schema and no output schema, the description covers the core purpose and supported modes. The only minor gap is the statement that it returns PNG while the format parameter allows jpeg/webp, and it does not explicitly mention the response is a binary image. Overall it is complete enough for an agent to invoke 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 coverage is 100% and every parameter (url, delay, style, format, dark_mode, full_page, viewport dimensions) has its own description. The tool description does not add any parameter-specific semantics beyond what the schema already provides, so the baseline 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 action ('Take a screenshot of a website') and the resource, and it enumerates the supported modes (viewport, full-page, mockup). This distinguishes it from the unrelated sibling check_balance and leaves no ambiguity about what the tool does.

  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 clear context for when to use the tool (capturing website screenshots) but does not include explicit when-not-to-use guidance or alternatives. Since the only sibling is unrelated, this is adequate and matches the 'clear context, no exclusions' level.

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

• check_balanceA
  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 states what the tool checks but doesn't explicitly disclose whether it is read-only, whether it consumes any resources, or if it requires authentication. Given the simplicity, it's likely non-mutating, but this is implied rather than stated. The description adds some value by specifying exactly what is checked, but lacks explicit behavioral guarantees.

  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 a single, efficient sentence that front-loads the core action ('Check your nightglass account balance') and immediately details the second element ('remaining screenshot credits'). No unnecessary words or filler. Every word 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?

  For a simple parameterless tool with no output schema, the description is nearly complete. It tells an agent what the tool does, and the return value (balance and credits) is implied. It doesn't specify the return format (e.g., JSON structure) but given the trivial nature, this is a minor gap. A 5 would require explicit mention of output format or side effects, which is not critical here.

  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?

  With 0 parameters and 100% schema coverage, the baseline is 4. The description doesn't need to explain parameters since there are none. It adds context about what the tool checks, but this is more about purpose than parameters. The score reflects that the description is sufficient for a parameterless tool.

  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 ('check') and clearly identifies the resource ('nightglass account balance' and 'remaining screenshot credits'). It inherently distinguishes from the sibling tool 'take_screenshot', which is about capturing screenshots, not checking balances. The purpose is 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 provides clear context by explaining what the tool does, which implicitly tells an agent when to use it (when balance or credit info is needed). It doesn't explicitly mention alternatives or exclusions, but with only one sibling, the distinction is obvious. This falls short of a 5 because it doesn't explicitly state 'use this when you need balance information rather than taking a screenshot'.

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