Server Quality Checklist

Tool Scores

• interactC
  2.3/5.0
  Behavior1/5

  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, but it says nothing about side effects, error handling, or element state requirements. It merely restates the action without revealing what happens on failure, waiting behavior, or whether it triggers navigation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single short sentence, making it concise. However, it is under-specified; it contains no concrete actions or context, which reduces its value. It is not verbose, but it also does not earn its place as a useful specification.

  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 the simple tool with three parameters, the description is too minimal to provide adequate context. It lacks information about interaction types, when to use it, and what outcomes to expect. The schema helps, but the description's vagueness leaves the overall picture incomplete.

  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 complete descriptions for all three parameters, so the baseline is 3. The description itself adds no parameter-level meaning, and it does not clarify the distinction between 'type' and 'fill' or when the 'value' is needed. However, the schema already covers the syntax.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose3/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description 'Interact with a page element' provides a verb and resource, but 'interact' is vague and does not specify the concrete actions (click, type, fill, select) that the schema reveals. It distinguishes from siblings like navigate or capture_screenshot, but not sharply enough to be immediately clear.

  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 usage guidance is provided. The description does not indicate when to use this tool over alternatives like execute_js or inspect_element, nor does it mention any prerequisites or exclusions. This leaves the agent without decision support.

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

• inspect_elementC
  2.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-only operation via 'Get', but does not state whether the tool executes JavaScript, what state it requires (e.g., page loaded), or what the return value looks like. It also does not disclose potential side effects or errors.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single sentence, which is concise and front-loaded. However, it is under-specified: it omits essential details about the output and the nature of parameters, which makes it less useful than a well-structured description. It is not as extreme as a tautology, but it lacks completeness.

  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?

  The tool has a simple schema (one required parameter) but no output schema and no annotations. The description does not explain what details are returned, what format they take, or any behavioral preconditions. This forces the agent to guess or invoke the tool to learn, which is incomplete for a tool with zero output schema coverage.

  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 tool description adds no parameter-specific meaning; it does not mention the 'selector' parameter. However, the input schema provides a clear description ('CSS selector of the element') with 100% coverage, 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.

  Purpose3/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states the tool retrieves details for an element ('Get details of a specific element'), which identifies the verb and resource. However, it lacks specificity about what 'details' includes (e.g., CSS styles, bounding box, attributes), and does not distinguish this from sibling tools like interact or execute_js.

  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?

  There is no guidance about when to use this tool compared to alternatives. The description only states the function without mentioning any context, prerequisites, or exclusion criteria.

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

• navigateC
  2.8/5.0
  Behavior2/5

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

  With no annotations available, the description alone must disclose behavioral traits. It only states the basic action without revealing whether it waits for page load, how it handles invalid URLs, or if it interacts with the existing viewport state. This leaves significant unknowns for the agent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, front-loaded sentence with no wasted words. However, it is so brief that it omits crucial details, making it slightly less useful than a concise but well-specified description.

  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?

  For a tool with three parameters, one nested object, no output schema, and no annotations, the description is incomplete. It does not explain return behavior, optional parameter usage, or any caveats, which is insufficient for confident tool invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is only 33% (only 'url' is described), and the description adds no meaning for 'isMobile' or 'viewport'. It fails to compensate for the low coverage, leaving the agent without understanding how these optional parameters affect navigation.

  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 ('Navigate') and the target ('a URL'), with a specific verb+resource. It naturally distinguishes itself from sibling tools like capture_screenshot or execute_js, which serve different purposes.

  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 is provided on when to use navigate versus alternatives like execute_js or interact. There is no mention of preconditions, such as needing a page to be already loaded, or when it is appropriate to navigate directly.

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

• get_network_trafficB
  3.1/5.0
  Behavior2/5

  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 does not mention that the 'clear' parameter can delete traffic after retrieval, nor does it describe output format, permissions, or 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?

  The description is a single, front-loaded sentence with no unnecessary words. It efficiently conveys the verb and resource.

  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 one optional parameter and full schema coverage, so the minimal description is adequate. However, it lacks any mention of return structure or side effects, leaving some context gaps.

  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 includes a description for the only parameter 'clear'. The tool description adds no extra parameter meaning, but baseline 3 is appropriate since the schema handles parameter semantics.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description states the verb 'Get' and the specific resource 'network requests and responses', which clearly distinguishes it from siblings like get_console_logs. It could be more specific about scope (e.g., current session, all network activity), but the core purpose is clear.

  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 is given on when to use this tool versus alternatives like get_console_logs or inspect_element. There is no context about debugging scenarios or exclusions.

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

• execute_jsB
  3.2/5.0
  Behavior2/5

  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 only states that arbitrary JS is executed, without mentioning potential side effects, page state changes, permission requirements, or what happens on errors. This is a significant gap for a tool that runs arbitrary code, which could alter the page or cause navigation.

  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, concise sentence with no unnecessary words or repetition. It effectively communicates the core action in the most efficient way possible, earning top marks for conciseness.

  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?

  Despite having only one parameter, the tool's complexity demands more context. The description does not explain what the tool returns (e.g., the script's result), how it handles async operations, or any risks associated with arbitrary code execution. This makes the description incomplete for safe and correct use.

  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 fully covers the only parameter 'script' with the description 'The JS code to execute'. The tool description adds no further semantic meaning beyond inferring that the script is JavaScript, so the baseline score of 3 is appropriate because the schema already handles the 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 'Execute arbitrary JavaScript in the browser context' uses a specific verb ('execute') and resource ('JavaScript in the browser context'), making the purpose immediately clear. It distinctly separates this tool from siblings like navigate, capture_screenshot, and get_console_logs, which all have different functions.

  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 is provided on when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or scenarios where other tools (e.g., interact, inspect_element) might be more appropriate, leaving the agent without clear decision-making support.

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

• capture_screenshotB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure. It only states the action, omitting important details such as whether it captures the viewport or full page, whether it returns a file path or base64, and whether it waits for page load. This is inadequate for a tool with no annotation support.

  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 concise sentence that is front-loaded and contains no fluff. It earns its place by clearly stating the core action.

  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?

  The tool is simple with one optional parameter and no output schema, but the description still leaves critical gaps: it does not explain what the tool returns, whether the screenshot is saved to a file, or what behavior to expect. For a tool without annotations, this is insufficient.

  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 only parameter, 'name', is fully described in the input schema as 'Optional name for the screenshot file' (100% schema coverage). The description adds no additional meaning, but the baseline of 3 is appropriate since the schema already covers the parameter semantics.

  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 'Take a screenshot of the current page' uses a specific verb ('take') and a clear resource ('screenshot of the current page'). It clearly distinguishes this tool from siblings like navigate, get_console_logs, or execute_js, which serve different purposes.

  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 intended use is implied: use this when a visual capture of the current page is needed. However, there is no explicit guidance on when not to use it or how it compares to alternatives, leaving the agent to infer the context from the tool's name.

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

• get_console_logsB
  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 carries the full burden of behavioral disclosure. It only states the core action, omitting any side effects (like clearing logs) or return format. The optional 'clear' parameter is defined in the schema but not mentioned in the description, so critical behavioral nuance is missing.

  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, concise sentence with no redundant wording. It is front-loaded and immediately communicates the tool's purpose, earning full marks for 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?

  The tool has no annotations, no output schema, and a minimal description. The description does not explain the return structure, potential volume of logs, or interactions with the 'clear' parameter. For a single-parameter tool, this is insufficient to fully guide an agent without additional context.

  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 100% because the only parameter 'clear' has a description ('Clear logs after retrieving'), so the schema already defines it. The description adds no additional meaning beyond the schema, making the baseline 3 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 'Get browser console logs' uses a specific verb ('get') and a clear resource ('browser console logs'), which distinguishes it from sibling tools like capture_screenshot or navigate. It is unambiguous and direct.

  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 clearly implies when the tool is needed (whenever console logs are desired), but it does not explicitly state when to prefer this tool over alternatives or mention any exclusions. For a simple getter, this is adequate but not exemplary.

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