Server Quality Checklist

Tool Scores

• get_active_windowA
  3.8/5.0
  Behavior3/5

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

  Discloses that it skips the assistant's own window, but with no annotations, it omits details on permissions, rate limits, or side effects; adequate but 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?

  Single sentence, 18 words, no redundancy, front-loaded with purpose.

  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?

  Covers key behavioral details and output scope, but lacks output format specification. Adequate for a simple read tool with no parameters.

  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?

  No parameters in schema; description correctly adds no param info. Baseline 4 for zero-param tools.

  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?

  Description clearly states the tool reports the active window's title, app, and URL for browsers, explicitly excluding the assistant's own window, distinguishing it from siblings.

  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?

  No guidance on when to use this tool versus siblings like get_clipboard or read_browser_page; lacks explicit context or alternatives.

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

• take_screen_snipA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry full behavioral disclosure. It states the action and outcome (screenshot returned as image) but omits details like permissions, output format, or potential side effects.

  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 concise sentences with no wasted words. Front-loaded with the core action, followed by usage guidance.

  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?

  The tool is simple with no params, but the description lacks details about the output format (e.g., image type, encoding) and error handling. For a screenshot tool, these are relevant for agent invocation.

  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?

  No parameters exist, so schema coverage is 100%. With 0 parameters, baseline is 4; the description adds no param info since none needed.

  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 takes a screenshot of the primary monitor and returns an image. It implicitly distinguishes from siblings by specifying 'visible on their screen' vs. active window, clipboard, etc.

  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?

  Explicitly says 'Use when the user asks about something visible on their screen,' providing clear context. It does not list exclusions, but the sibling tools imply alternatives.

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

• read_browser_pageA
  4.3/5.0
  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 of behavioral disclosure. It clearly indicates a read-only operation, specifies that it works across major browsers, notes it functions even when the browser is unfocused, and states the return value (URL plus page text). It could mention limitations like non-text content or missing permissions, but it is transparent for this simple 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?

  Two concise, well-structured sentences: the first states the primary action and scope, and the second states the return value. There is no redundant information or padding.

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

  Completeness5/5

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

  For a simple tool with one optional parameter and no output schema, the description is sufficiently complete. It explains the input scope, cross-browser support, unfocused-window behavior, and the exact return contents, leaving little ambiguity for an agent selecting or invoking it.

  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 single parameter max_chars is already fully described in the schema as 'Optional cap on returned characters', giving 100% schema coverage. The description does not add further parameter-level detail, 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 identifies the action ('Read the text of the page'), the target resource ('page open in the user's visible browser window'), and even enumerates supported browsers. It distinguishes itself from sibling tools like get_selected_text or take_screen_snip by specifying it captures full page text plus URL.

  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 provides clear context for when to use the tool: when you need the text of the currently visible browser page, even if the browser is not focused. It does not explicitly state when not to use it or name alternatives, but the scope is understandable from the description alone.

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

• get_selected_textA
  4.6/5.0
  Behavior4/5

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

  Without annotations, the description discloses behavioral traits such as the dependency on the last used app and the recommended fallback to clipboard. It implies it is read-only and non-destructive, but could be more explicit about return type or permissions. Overall, it adds useful context beyond the schema.

  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 three short sentences, each with a clear purpose: primary function, optimal usage context, and fallback instruction. No unnecessary words, and information is 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?

  The description covers the main task, usage context, and alternative. It lacks details about the return format (e.g., string) but for a simple read tool with no output schema, it is fairly complete. It adequately serves an AI agent's needs.

  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?

  The input schema has zero parameters, so the description is not required to explain them. The baseline for no parameters is 4, and the description does not need to add parameter info. It focuses on the tool's behavior, which 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 reads highlighted text from the desktop. It differentiates from sibling tools like get_clipboard by describing when to use each. The verb 'Read' and resource 'text the user currently has highlighted' 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 Guidelines5/5

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

  The description provides explicit guidance on when to use this tool versus the alternative get_clipboard. It says to use get_clipboard if get_selected_text returns no selection. It also notes it works best when the selection is in the last used app, giving context for optimal use.

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

• get_clipboardA
  4.7/5.0
  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 two key behavioral traits: cross-platform reliability and no need for window focus. It doesn't mention return format or failure modes, but for a simple clipboard read, these traits add meaningful value beyond the tool's name.

  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, well-structured sentence. It front-loads the core purpose, then adds reliability and usage context, with no redundant words.

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

  Completeness5/5

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

  For a tool with no parameters and no output schema, the description fully covers the essential information: what it reads, when to use it (fallback), and a key advantage (no focus needed). Sibling differentiation is handled, making this complete in context.

  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?

  The tool has zero parameters and the schema is empty, so the description does not need to explain parameters. Per baseline for 0-param tools, a score of 4 is appropriate; the description adds no parameter details because none exist.

  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 starts with a specific verb and resource: 'Read the user's current clipboard text.' It clearly distinguishes itself from the closest sibling by positioning as 'the fallback when get_selected_text returns nothing', making its unique role explicit.

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

  Usage Guidelines5/5

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

  It provides explicit usage guidance: use as fallback when get_selected_text returns nothing. It also adds context that it is reliable on all platforms and needs no window focus, helping the agent decide when this tool is preferable.

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