Server Quality Checklist

Tool Scores

• comet_screenshotB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but only states the basic action. It doesn't disclose behavioral traits such as what format the screenshot is captured in (PNG, JPEG), whether it requires specific permissions, if it captures the entire page or viewport, or how the result is returned. This leaves significant gaps for a tool that presumably produces output.

  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 front-loads the core action. There is zero waste, and every word ('capture', 'screenshot', 'current page') contributes directly to understanding the tool's function.

  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 a simple but potentially output-producing tool, the description is incomplete. It doesn't explain what the screenshot output looks like (e.g., file, base64, path) or any behavioral nuances, leaving the agent with insufficient context to use it effectively beyond the basic action.

  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 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here, but it could mention implicit context (e.g., 'current page' refers to an active browser tab). Baseline is 4 for zero parameters.

  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 ('capture') and target ('screenshot of current page'), making the purpose immediately understandable. It doesn't differentiate from siblings like comet_tabs or comet_upload, but the verb+resource combination is specific enough for basic understanding.

  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 like comet_tabs (which might list tabs) or comet_upload (which might upload files). The description implies usage when a screenshot is needed, but offers no context about prerequisites, timing, or exclusions.

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

• comet_stopB
  3.3/5.0
  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. It states the tool stops a task but doesn't disclose behavioral traits such as whether this is reversible, what happens to in-progress work, permission requirements, or side effects. This is a significant gap for a control tool with mutation implications.

  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 directly states the tool's function and condition without any fluff. It's front-loaded and every word earns its place, making it highly concise and well-structured.

  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 (it's a control/mutation tool with no annotations and no output schema), the description is incomplete. It lacks details on behavior, outcomes, or error handling, which are crucial for safe and effective use. The schema's parameter coverage doesn't compensate for these missing contextual elements.

  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 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add param info, which is fine here, but it doesn't compensate for any gaps either. A baseline of 4 is appropriate as the schema fully handles the lack of parameters.

  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 with a specific verb ('Stop') and target ('the current agent task'), and it provides a condition ('if it's going off track') that adds specificity. However, it doesn't explicitly differentiate this from sibling tools like comet_mode or comet_poll, which might also affect agent behavior, so it falls short of a perfect score.

  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 usage guidelines by specifying 'if it's going off track,' which suggests when to use this tool—when corrective action is needed. However, it doesn't provide explicit alternatives (e.g., vs. comet_ask for clarification) or exclusions, leaving some ambiguity about optimal scenarios compared to siblings.

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

• comet_connectB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses that the tool may auto-start the browser if needed, which is useful behavioral context beyond just 'connect'. However, it lacks details on permissions, error handling, or what 'connect' entails operationally (e.g., establishes a session, verifies readiness).

  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 front-loads the main action ('Connect to Comet browser') and adds a critical behavioral note ('auto-starts if needed') without any wasted words. Every part earns its place.

  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 the tool's simplicity (0 parameters, no annotations, no output schema), the description is adequate but minimal. It covers the core action and a key behavior, but for a tool that likely establishes a critical connection, more context on what 'connect' means or post-conditions would be helpful.

  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 0 parameters, and schema description coverage is 100% (empty schema). The description doesn't need to explain parameters, so it meets the baseline of 4 for parameterless tools by not introducing confusion.

  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 ('Connect to Comet browser') and includes an important behavioral detail ('auto-starts if needed'), which specifies what happens when the browser isn't running. It doesn't explicitly differentiate from siblings like comet_stop or comet_tabs, but the verb 'connect' is specific enough to understand the core function.

  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 no guidance on when to use this tool versus alternatives like comet_stop or comet_ask. It mentions auto-starting, which implies a prerequisite (browser might not be running), but doesn't state explicit conditions or exclusions for usage.

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

• comet_tabsA
  3.6/5.0
  Behavior3/5

  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 mentions the tool 'shows all open tabs' and helps 'coordinate multi-tab workflows,' which gives some behavioral context, but doesn't address important aspects like whether this requires browser permissions, if it works across browser windows, what happens when switching/closing tabs, or any rate limits. The description adds basic value but leaves significant gaps for a mutation-capable 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 appropriately sized with two sentences that each serve a purpose: the first states core functionality, the second adds value context. It's front-loaded with the primary purpose. While efficient, the second sentence could be slightly more precise about what 'coordinate' entails.

  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 the tool has 3 parameters with full schema coverage but no annotations and no output schema, the description provides a reasonable foundation but has gaps. For a tool that can perform mutations (switch/close tabs), more behavioral context would be helpful, especially regarding permissions, side effects, and return values. The description is minimally adequate but not fully complete for this complexity level.

  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 three parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, such as explaining how 'domain' matching works or what 'tabId' format to expect. The baseline score of 3 reflects adequate parameter documentation entirely through the schema.

  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 with specific verbs ('view and manage') and resources ('browser tabs'), and distinguishes it from sibling tools by mentioning its unique functionality for coordinating multi-tab workflows without duplicates. It goes beyond the name/title to explain what the tool actually does.

  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 usage context ('helps coordinate multi-tab workflows without creating duplicate tabs'), suggesting when this tool might be beneficial, but doesn't explicitly state when to use it versus alternatives or provide exclusions. No sibling tool comparisons are made, leaving the agent to infer appropriate usage scenarios.

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

• comet_pollA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It discloses that this is a monitoring tool meant for repeated calls, which suggests it's non-destructive and likely read-only. However, it doesn't specify authentication needs, rate limits, what 'status and progress' includes, or error behaviors. The description adds some context but leaves behavioral traits incomplete for a tool with zero annotation coverage.

  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 perfectly concise: two sentences that each earn their place. The first states the purpose, the second provides usage guidance. No wasted words, front-loaded with essential information. It's appropriately sized for a simple polling tool.

  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 zero parameters, no annotations, and no output schema, the description provides adequate basic information but has gaps. It explains what the tool does and when to use it, but doesn't describe what 'status and progress' returns or any behavioral constraints. For a monitoring tool in an agentic context, more detail about return values or polling behavior would be helpful.

  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 0 parameters with 100% schema description coverage (empty schema). The description doesn't need to add parameter details, so it appropriately focuses on usage. Baseline for 0 parameters is 4, as there's no parameter information to compensate for. The description's mention of 'call repeatedly' adds useful semantic context about invocation patterns.

  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: 'Check agent status and progress' provides a specific verb ('check') and resource ('agent status and progress'). It distinguishes from siblings like comet_ask or comet_upload by focusing on monitoring rather than interaction or file operations. However, it doesn't explicitly differentiate from comet_stop or comet_mode which might also relate to agent state.

  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 for usage: 'Call repeatedly to monitor agentic tasks' indicates this is for polling/monitoring scenarios. It implies usage during ongoing tasks but doesn't specify when NOT to use it or name alternatives among siblings. The guidance is helpful but lacks explicit exclusions or comparisons to other tools.

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

• comet_askA
  3.9/5.0
  Behavior3/5

  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 adds useful context by stating it's a 'blocking' call and mentions use cases like handling 'login walls, dynamic content, filling forms,' which implies real-time interaction capabilities. However, it lacks details on error handling, rate limits, or authentication needs, leaving gaps in behavioral understanding.

  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 front-loaded with the core purpose in the first sentence and efficiently adds context in the second. Every sentence earns its place by clarifying use cases without redundancy, making it appropriately sized and well-structured.

  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 the tool's complexity (blocking call with browser interaction) and no annotations or output schema, the description is moderately complete. It covers key behavioral aspects like blocking nature and use cases, but lacks details on return values, error conditions, or performance constraints, which are important for a tool with real-time dependencies.

  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 does not add any additional meaning or examples beyond what the schema provides for parameters like 'prompt' or 'context.' Baseline score of 3 is appropriate as the schema handles the heavy lifting without description enhancement.

  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 ('Send a prompt to Comet/Perplexity and wait for the complete response') and distinguishes this tool from its siblings by specifying it's 'blocking' and 'ideal for tasks requiring real browser interaction or deep research with agentic browsing.' This differentiates it from non-blocking or non-browser interaction tools in the sibling list.

  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 this tool ('Ideal for tasks requiring real browser interaction... or deep research with agentic browsing'), which helps differentiate it from siblings like comet_screenshot or comet_tabs. However, it does not explicitly state when not to use it or name specific alternatives, such as when non-blocking calls might be preferred.

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

• comet_uploadA
  3.9/5.0
  Behavior3/5

  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 adds useful context beyond the input schema, such as the file needing to exist locally and the auto-detection fallback for selectors. However, it does not cover important behavioral aspects like error handling, permissions, or what happens after upload, leaving gaps for a mutation 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 appropriately sized and front-loaded, with three concise sentences that each earn their place: stating the action, providing usage context, and specifying a key constraint. There is zero waste, making it efficient and easy to parse for an AI agent.

  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 the tool's complexity (mutation with 3 parameters) and no annotations or output schema, the description is moderately complete. It covers the purpose, usage context, and a key constraint, but lacks details on behavioral outcomes, error cases, or post-upload effects, which are important for a file upload operation without structured support.

  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, mentioning the local filesystem requirement which relates to filePath but does not 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 ('upload a file') and target resource ('to a file input on the current page'), distinguishing it from siblings like comet_screenshot or comet_tabs. It specifies the file types (images, documents, other files) and contexts (forms, posts, upload dialogs), providing comprehensive purpose clarity.

  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 for when to use this tool ('to attach images, documents, or other files to forms, posts, or upload dialogs'), but does not explicitly state when not to use it or name alternatives among sibling tools. It implies usage for file uploads on web pages, which is helpful but lacks explicit exclusions or comparisons.

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

• comet_modeA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It describes the action (switching modes or checking current) and lists mode options, but lacks details on permissions needed, side effects, or error handling. It's adequate but minimal.

  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 sentences: first states purpose and lists modes with brief explanations, second explains optional usage. Every word adds value, no redundancy, and it's front-loaded with key 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?

  For a simple tool with one optional parameter and no output schema, the description covers purpose, usage, and parameter meaning adequately. It could be more complete by mentioning return values or errors, but given the low complexity, it's mostly sufficient.

  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 the optional 'mode' parameter with enum values. The description adds context by explaining what each mode does and the behavior when omitted, but doesn't provide additional syntax or format details beyond the schema.

  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 ('Switch') and resource ('Perplexity search mode'), specifies the four available modes with brief explanations, and distinguishes this tool from siblings by focusing on mode switching rather than asking questions, connecting, polling, etc.

  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 ('Switch Perplexity search mode') and provides clear alternatives for different actions (call without mode to see current mode vs. with mode to switch). It differentiates from sibling tools by its specific function.

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