Server Quality Checklist

Tool Scores

• review_routesC
  2.1/5.0
  Behavior1/5

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

  No annotations are provided, so description must fully disclose behavioral traits. It only says 'review', giving no indication of read/write nature, side effects, or output characteristics.

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

  Conciseness2/5

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

  Description is a single sentence, but it is under-specified rather than concise. Key information is missing; it cannot be considered efficiently structured.

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

  Completeness1/5

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

  With 9 parameters, no output schema, and no annotations, the description is severely incomplete. It fails to cover return values, behavior, or how results are presented.

  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% (3 of 9 params documented). The description adds no parameter meaning beyond the schema; it does not explain the undocumented params like model, format, provider, viewports.

  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 'Review multiple routes of an application' which is a clear verb-resource combination. However, it does not differentiate from sibling tools like review_url (single URL) or review_flow (likely a sequence), missing an opportunity to clarify scope.

  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 alternatives. No prerequisites, limitations, or context for usage provided.

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

• get_latest_reportC
  2.8/5.0
  Behavior2/5

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

  No annotations are present, so the description must cover behavioral traits. It only states 'Return' (implying read-only) but does not explain how the 'most recent' report is determined, what happens if no report exists, or any side effects. This is insufficient 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.

  Conciseness4/5

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

  The description is a single concise sentence with no wasted words. It front-loads the key information (action and resource). However, it could be slightly expanded to include parameter or behavior hints without becoming lengthy.

  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 lack of output schema and annotations, the description should provide more context about the report content, how recency is determined, and error handling. For a simple one-parameter tool, it is still incomplete and leaves the agent guessing.

  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?

  The schema has one optional parameter 'format' with enum values 'md' and 'json', but the description does not mention it or explain its effect. With 0% schema description coverage, the description must compensate, but it provides no parameter information.

  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 ('Return'), the resource ('UX review report content'), and a specific qualifier ('most recent'). This distinguishes it from siblings like review_url or tune_animations, which have 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 this tool vs alternatives like review_flow or review_routes. The description lacks any context about prerequisites, scenarios, or exclusions.

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

• review_urlB
  3.1/5.0
  Behavior2/5

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

  The description does not disclose behavioral traits beyond the basic function. With no annotations, the description carries the full burden. It fails to mention whether the tool is read-only, whether it modifies any state, auth requirements, rate limits, or what happens during capture (e.g., network requests). The phrase 'using vision AI' hints at the mechanism but is insufficient.

  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 sentence that conveys the core purpose without wasted words. It is appropriately concise for a tool with a self-explanatory name, though it could benefit from slightly more detail without becoming verbose.

  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 10 parameters, no output schema, and no annotations, the description is too minimal. It does not explain return values, expected outcomes, or how parameters influence behavior. The extensive parameter list is left entirely to the schema descriptions, which lack contextual guidance for an agent.

  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%, so the baseline is 3. The description adds no additional parameter-level meaning beyond what the schema already provides. It is generic and does not explain the significance or typical usage of any 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 clearly states the tool captures and analyzes a URL for UI/UX issues using vision AI. The verb 'capture and analyze' combined with the specific resource 'URL' makes the purpose unambiguous. It also naturally distinguishes from siblings like review_routes or review_flow, which address different scopes.

  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. While the purpose is clear, there is no mention of context, prerequisites, or when not to use it. The presence of sibling tools (e.g., review_routes, review_flow) highlights the need for such differentiation, but the description offers none.

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

• review_flowA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It clearly explains the tool's behavior: capturing frame bursts after each interaction and using a vision LLM to grade multiple aspects. While it doesn't detail potential side effects (e.g., execution time, network usage), it sufficiently communicates the non-destructive, review-oriented nature. Minor improvement could mention that it runs browser actions.

  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 sentences states the core function; the second provides usage guidance. It is front-loaded and every word adds value. No extraneous information.

  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 tool has 10 parameters and no output schema. The description explains the purpose and expected output (grading of animation quality, etc.), which is sufficient for an agent to understand what the tool does. It does not detail return format, but the context of 'grades' implies a report. For a complex tool, this is fairly complete, though mentioning the artifact output could improve clarity.

  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%, so the baseline is 3. The description does not add parameter-level details but provides overarching context. It does not compensate for any missing schema information, which is unnecessary here due to full coverage. Thus a 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 specifies a clear verb ('Run a scripted user-flow review'), resource ('a URL'), and scope ('captures frame bursts... grades animation quality'). It distinguishes itself from the sibling tool 'review_url' by explicitly stating it is for flow/animations, not static design.

  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?

  Explicitly states when to use ('when the user asks about animations, interaction states, or whether a flow feels good') and when not to ('NOT for static design issues'), naming the alternative 'review_url'. This provides clear decision guidance.

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

• tune_animationsA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It details the detection of multiple animation libraries, generation of an interactive tuner, and export functionality. It lacks explicit mention of potential side effects beyond writing a file, but overall 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 a single concise paragraph of three sentences, front-loaded with the core action and outcome. No redundant or unnecessary information.

  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 main behavior, use case, and return value. It lacks details on error handling or edge cases (e.g., no animations found), but given no output schema and full parameter documentation, it is sufficiently complete.

  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% with all 5 parameters described. The description does not add additional semantics beyond the schema definitions, meeting the baseline expectation.

  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 that the tool detects animations and generates an interactive tuner HTML page, specifying supported animation libraries. It distinguishes itself from sibling tools like review_url by explicitly focusing on tuning rather than reviewing.

  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 includes an explicit usage statement: 'Use when the user wants to fine-tune existing animation parameters, NOT to review for issues.' This directly contrasts with the review-focused sibling tools.

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