Server Quality Checklist

Tool Scores

• get_console_logsB
  3.4/5.0
  Behavior2/5

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

  There are no annotations, so the description carries the full burden. It merely says 'get console output' without disclosing return format, ordering, buffering behavior, or whether reading the logs clears them. The sibling clear_buffers suggests a buffer relationship, but this is not addressed.

  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 immediately states the tool's purpose and scope. All words are relevant, and it is properly front-loaded with 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?

  Given the presence of siblings like clear_buffers and no output schema, the description is too terse. It does not explain what the returned logs look like, whether they are cumulative, or if the call has side effects on the buffer. This leaves important gaps for an agent selecting the tool.

  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 covers all three parameters (level, limit, url_filter) with descriptions and defaults, so the schema provides full parameter semantics. The tool description adds no additional meaning beyond what the schema already states, which is the baseline 3.

  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 retrieves browser console output with three log levels (error/warn/log). This is specific and distinguishes it from the sibling get_browser_errors by covering all console levels, not just errors.

  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 the tool is for fetching console logs but gives no explicit guidance on when to prefer it over get_browser_errors or how it relates to clear_buffers. Usage context is only implied through the tool's name and description.

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

• get_browser_errorsA
  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 of behavioral disclosure. It does disclose the scope (uncaught exceptions + unhandled promise rejections) and included data (message, stack trace, DOM context), but it does not mention whether the tool is read-only, whether it clears errors, or any limitations (e.g., buffer size beyond the limit parameter).

  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, front-loaded with the core purpose and followed by key specifics. Every clause adds value without redundancy, making it appropriately concise and well-structured.

  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?

  Given the tool's low complexity, optional parameters, and no output schema, the description covers the essential behavior. It might benefit from noting that it returns a list of errors or that it does not affect browser state, but the current description is sufficiently complete for basic usage.

  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%: both 'limit' and 'url_filter' have clear descriptions. The tool description adds no additional parameter semantics beyond what the schema already provides, so the baseline score of 3 applies.

  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's purpose: to retrieve browser runtime errors (uncaught exceptions and unhandled promise rejections). It specifies the resource ('browser runtime errors') and the verb ('取得' / get), and distinguishes itself from sibling tools like get_console_logs by targeting errors rather than logs.

  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 makes it clear this tool is for debugging runtime errors, which implies when to use it. However, it does not explicitly mention alternatives or exclusions (e.g., 'use get_console_logs for console messages'), so it lacks explicit when-not-to-use guidance, but the context is clear enough.

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

• get_page_infoA
  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 full behavioral disclosure burden. It states that the tool lists currently tracked pages and buffer statistics, indicating a read-only operation, but it does not explicitly confirm safety, permissions, or side effects. It could benefit from stating that this is a non-mutating inspection 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 a single, well-structured sentence that starts with the action verb and includes key output components. It is concise with no unnecessary wording.

  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, read-only listing tool, the description provides adequate context: it specifies the exact data returned (pages with URL/title/last activity, buffer stats) and implies the current state. Without an output schema, the description covers essential return values, though it could elaborate on the format of buffer statistics.

  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 no parameters, and the schema is empty, so parameter semantics are trivially covered. The description adds context about the return payload (URL, title, last activity, buffer stats), which clarifies the tool's output without needing parameter explanations. Baseline 4 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 the specific verb '列出' (list) and clearly identifies the resource as pages tracked by the extension, including URL, title, and last activity time, plus buffer statistics. This distinguishes it from sibling tools like get_browser_errors and get_console_logs, which address errors and logs respectively.

  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 does not provide explicit when-to-use or alternative guidance. It clearly explains that the tool returns page tracking info, implying it is used when page data is needed, but no exclusions or alternative tools are mentioned.

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

• clear_buffersA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It explicitly states that the tool clears error and log buffers, which indicates a destructive action on accumulated data. However, it does not mention side effects, irreversibility, or any impact beyond the buffers, leaving some behavioral ambiguity.

  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 extremely concise, with two short sentences. The first sentence states the primary action, and the second provides the intended use case. No wasted 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?

  Given the simplicity of the tool (no parameters, no output schema, clear action), the description fully covers what the tool does and when to use it. It is complete and adequate 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.

  Parameters4/5

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

  The tool has zero parameters, so the schema is fully covered. The description correctly omits parameter details, and the baseline of 4 applies since no parameter explanation is 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 verb ('清空' / clear) and the specific resources ('錯誤與 log 緩衝區' / error and log buffers). This distinguishes it from sibling getter tools like get_browser_errors and get_console_logs by signaling a mutating action.

  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 a clear usage context: to eliminate old noise before re-observing. It implies this is a reset/preparation step, though it does not explicitly mention when not to use it or list alternative tools.

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