Server Quality Checklist

Tool Scores

• extract_schemaD
  1.1/5.0
  Behavior1/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure but fails completely. It doesn't indicate whether this is a read or write operation, what permissions are required, what happens during extraction, whether it's destructive, or what the expected behavior is. The phrase 'Reserved mapping' is particularly opaque about actual tool behavior.

  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?

  While technically concise with just one phrase, this is a case of harmful under-specification rather than effective brevity. The single sentence doesn't earn its place by providing meaningful information - it's so vague that it fails to communicate basic tool functionality.

  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?

  Given a tool with 2 required parameters, nested object schema, no output schema, and no annotations, this description is completely inadequate. It provides no information about what the tool does, how to use it, what the parameters mean, or what to expect as a result. The description fails to compensate for the lack of structured documentation.

  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?

  With 0% schema description coverage for both parameters (url and schema), the description provides absolutely no information about what these parameters mean, their expected formats, or how they relate to the extraction process. The description doesn't mention parameters at all, leaving two required parameters completely undocumented.

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

  Purpose1/5

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

  The description 'Reserved mapping for extraction path' is vague and tautological - it essentially restates the tool name 'extract_schema' without specifying what resource is being extracted from what source or what the extraction actually does. It provides no meaningful verb+resource combination that distinguishes this tool from its siblings.

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

  Usage Guidelines1/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any context, prerequisites, or relationships to sibling tools like close_session, get_a11y_tree, interact, navigate, or screenshot. There's no indication of when this extraction operation is appropriate.

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

• interactC
  2.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'active session' which implies statefulness, but doesn't describe what happens if the session isn't active, whether actions are synchronous/asynchronous, error conditions, or what constitutes success/failure. For a UI interaction tool with mutation potential, this is inadequate behavioral context.

  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 extremely concise at just 7 words, which is appropriate for a simple concept. It's front-loaded with the core functionality. However, the brevity comes at the cost of completeness - it could benefit from one more clarifying sentence 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?

  For a UI interaction tool with 3 parameters, no annotations, no output schema, and 0% schema description coverage, the description is insufficient. It doesn't explain what gets returned, error handling, session management requirements, or the scope of 'click/fill' actions. The agent would struggle to use this tool effectively without trial and error.

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

  Parameters2/5

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

  With 0% schema description coverage for 3 parameters, the description provides no information about parameter meanings. It doesn't explain what 'session_id' refers to, what 'click' vs 'fill' actions entail, or what the 'params' object should contain. The description fails to compensate for the complete lack of schema documentation.

  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 performs 'click/fill style actions in active session', which provides a general purpose but lacks specificity about what resources are being acted upon. It distinguishes from siblings like 'close_session' or 'navigate' by focusing on UI interactions, but doesn't specify what elements can be clicked/filled or how this differs from similar tools that might exist.

  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?

  The description provides minimal guidance - it implies usage when needing to interact with UI elements in an active session, but offers no explicit when-to-use rules, no prerequisites (like needing an active session first), and no alternatives to consider. It doesn't help the agent decide between 'click' vs 'fill' actions or when to use this versus other interaction tools.

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

• close_sessionC
  2.7/5.0
  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. It mentions clearing MCP state, which implies a destructive action, but doesn't detail what 'clear' entails (e.g., data loss, resetting configurations) or any prerequisites like authentication needs. The behavioral impact is under-specified for a state-altering tool.

  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 is front-loaded with the main action, making it efficient. However, the phrase 'only when closing the currently stored session' is slightly redundant and could be more precise, but overall, it's concise with minimal waste.

  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 tool's complexity (state-clearing action), lack of annotations, no output schema, and 0% schema coverage, the description is incomplete. It fails to explain parameters, behavioral consequences, or usage context adequately, leaving significant gaps for an AI agent to understand and invoke the tool correctly.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate. It doesn't explain the 'session_id' parameter at all—no context on what it is, how to obtain it, or its format. The description adds no meaning beyond the bare schema, leaving the parameter undocumented.

  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?

  The description clearly states the action ('Close current session') and the resource ('MCP state'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'interact' or 'navigate' which might also manage sessions, and the phrase 'only when closing the currently stored session' is somewhat redundant with the tool name.

  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?

  The description provides minimal guidance with 'only when closing the currently stored session', but this is vague and doesn't explain when to use this tool versus alternatives or what 'currently stored session' means in context. No explicit when/when-not scenarios or sibling tool comparisons are included.

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

• get_a11y_treeC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries full burden but only states what it does without behavioral details. It doesn't disclose if this is read-only, has side effects, requires specific permissions, or how it handles errors, leaving significant gaps for a tool that interacts with sessions.

  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 with no wasted words, clearly front-loading the purpose. It's appropriately sized for a simple tool with one parameter.

  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 no annotations, no output schema, and low schema coverage, the description is incomplete. It lacks details on behavioral traits, parameter specifics, and expected output, making it inadequate for a tool that likely returns structured accessibility data.

  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 0%, but the description implies the 'session_id' parameter is needed for an 'active session'. However, it doesn't add meaning beyond this basic context, such as format or source of the session ID, so it only partially compensates for the lack of schema documentation.

  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?

  The description clearly states the verb ('Get') and resource ('accessibility tree snapshot'), specifying it's for an 'active session'. However, it doesn't differentiate from sibling tools like 'extract_schema' or 'screenshot', which might also retrieve session-related data.

  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 mentions 'active session' but doesn't specify prerequisites, such as requiring an open session, or contrast it with other tools like 'screenshot' for visual data.

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

• screenshotC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It mentions that 'Explicit session_id is persisted as active session context,' adding some context about session management. However, it fails to disclose critical traits like whether this is a read-only or mutative operation, potential side effects (e.g., file creation, permissions needed), or output format (e.g., image data, file path). This leaves significant gaps for a tool that likely involves system interaction.

  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 concise with two sentences that are front-loaded with the core purpose. Every sentence adds value: the first states the action, and the second provides context about session persistence. There's no wasted text, though it could be slightly more structured for clarity.

  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 tool's complexity (screenshot capture likely involves system operations), no annotations, no output schema, and low schema coverage, the description is incomplete. It lacks details on behavior, output, error handling, and parameter usage, making it inadequate for safe and effective use by an AI agent.

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

  Parameters2/5

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

  The input schema has 2 parameters with 0% description coverage, so the description must compensate. It mentions 'session_id' and implies 'url' through 'standalone,' but doesn't explain their semantics (e.g., what a session_id refers to, format of url, whether both can be used together, defaults). This adds minimal meaning beyond the bare schema, insufficient for the low coverage.

  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?

  The description clearly states the tool's purpose as 'Take in-session or standalone screenshot,' specifying the action (take screenshot) and scope (in-session or standalone). It distinguishes from siblings like 'navigate' or 'interact' by focusing on capturing visual output. However, it doesn't explicitly differentiate from potential screenshot-related siblings if they existed, keeping it at 4 rather than 5.

  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 provides implied usage guidance by mentioning 'in-session or standalone' and that 'Explicit session_id is persisted as active session context,' suggesting when to use session_id vs. url. However, it lacks explicit when-to-use vs. alternatives (e.g., compared to 'extract_schema' or 'get_a11y_tree' for data extraction) or clear exclusions, so it's not fully explicit.

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

• navigateA
  4.1/5.0
  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 effectively describes key behaviors: automatic session creation, stealth mode's purpose (reduce bot detection with realistic user agent and hidden webdriver flag), and action delay for politeness. However, it doesn't cover error handling or response format.

  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 efficiently structured in three sentences, each earning its place: core action, session management, and parameter usage tips. It's front-loaded with the main purpose and avoids unnecessary details.

  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?

  Given no annotations and no output schema, the description is moderately complete for a tool with 4 parameters and 100% schema coverage. It covers key behaviors but lacks details on return values, error cases, or prerequisites. For a navigation tool with potential complexities, it could benefit from more 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%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by briefly mentioning use cases for 'stealth' and 'action_delay_ms', but doesn't provide additional syntax or format details. Baseline 3 is appropriate as the schema does the heavy lifting.

  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 specific action ('Navigate to a URL') and resource (URL), distinguishing it from siblings like 'close_session' or 'screenshot' which perform different operations. It goes beyond just restating the name by explaining the core functionality.

  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 on when to use certain parameters ('Use stealth: true when visiting public sites', 'Use action_delay_ms to add polite jitter'), but does not explicitly state when to use this tool versus alternatives like 'interact' or 'extract_schema'. It offers practical guidance without naming specific sibling tools.

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