Server Quality Checklist

Tool Scores

• browser_inspect_consoleB
  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 the full burden of behavioral disclosure. It states what the tool does but lacks critical details: it doesn't specify if this is a read-only operation, whether it requires specific permissions, how it captures logs (e.g., real-time vs. buffered), or any rate limits. The mention of 'captured' hints at stored data but doesn't clarify behavior beyond the basic action.

  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 well-structured and front-loaded, with the core purpose in the first sentence and additional details in a clear 'Args'/'Returns' format. Every sentence earns its place by providing essential information without redundancy, making it efficient and easy to parse.

  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 moderate complexity (single parameter, no annotations, but with an output schema), the description is partially complete. It explains the purpose and return format, but lacks usage guidelines, behavioral context, and full parameter semantics. The output schema mitigates the need to detail return values, but other gaps remain, making it adequate but with clear room for improvement.

  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 description explicitly documents the 'session' parameter, adding meaning beyond the input schema (which has 0% description coverage). However, it only names the parameter without explaining its semantics (e.g., what constitutes a valid session name, how to obtain it from sibling tools like 'browser_session_list'). With one parameter and low schema coverage, this provides some compensation but leaves gaps.

  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 ('Get') and resource ('captured console log messages from the page'), making it immediately understandable. However, it doesn't explicitly distinguish this from sibling tools like 'browser_inspect_dom' or 'browser_inspect_events', which also inspect page elements but target different resources.

  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. It doesn't mention prerequisites (e.g., requiring an active browser session), exclusions, or how it differs from other inspection tools like 'browser_inspect_text' or 'browser_inspect_network', leaving the agent to infer usage context from the tool name alone.

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

• browser_session_listB
  3.2/5.0
  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 states the tool lists sessions and returns specific data, but doesn't cover important aspects like whether it's read-only (implied by 'List' but not explicit), potential errors if no sessions exist, or performance considerations. For a tool with zero annotation coverage, this is a significant gap in transparency.

  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 and well-structured: a clear purpose statement followed by a bullet-point-like return format. Every sentence earns its place by providing essential information without waste, making it easy for an AI agent to parse quickly.

  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 low complexity (0 parameters, no annotations) and the presence of an output schema, the description is adequate but minimal. It explains what the tool does and the return format, which is sufficient for basic use. However, it lacks context on behavioral traits like error handling or session state dependencies, leaving some gaps in completeness.

  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 appropriately doesn't discuss parameters, focusing instead on the return values. This meets the baseline for tools with no parameters, as it avoids redundancy and adds value by explaining the output.

  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 ('List') and resource ('browser sessions'), including what information is returned. It distinguishes from siblings like 'browser_session_connect' or 'browser_session_destroy' by focusing on listing rather than modifying sessions. However, it doesn't explicitly differentiate from all siblings (e.g., 'browser_inspect_*' tools), keeping it from 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 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. It doesn't mention prerequisites, such as needing active sessions to list, or compare it to other tools like 'browser_session_connect' for session management. This lack of contextual usage information limits its effectiveness for an AI agent.

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

• browser_inspect_eventsA
  3.5/5.0
  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 usefully adds that 'The event log is append-only and records all tool calls made to this session,' which clarifies the log's nature and content. However, it doesn't mention potential limitations like log size, retention policies, or authentication requirements, leaving gaps for a mutation-free read operation.

  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 with a clear purpose statement followed by bullet points for arguments and returns. Every sentence adds value: the first defines the tool, the second explains the event log's behavior, and the bullet points document parameters and output. There is no redundant or wasted text.

  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 (one parameter, no nested objects) and the presence of an output schema (which handles return value documentation), the description is reasonably complete. It covers purpose, parameter semantics, and output format. However, it lacks usage guidelines and some behavioral details like error conditions or session state requirements, preventing a perfect score.

  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 description adds meaningful context beyond the input schema. The schema only defines 'session' as a required string parameter with 0% description coverage. The description clarifies that 'session' refers to the 'Name of the browser session,' providing essential semantic information that the schema lacks. This compensates well for the low schema 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: 'Get the event log for a session' with the specific resource being 'event log' and verb 'Get'. It distinguishes from siblings like browser_inspect_console or browser_inspect_dom by focusing on tool call events rather than console output, DOM structure, or other session aspects. However, it doesn't explicitly contrast with all sibling tools, keeping it at a 4 rather than a 5.

  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. It doesn't mention when this tool is appropriate compared to other browser_inspect_* tools or browser_session_* tools, nor does it specify prerequisites like needing an active session. The agent must infer usage from the tool name and description alone.

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

• browser_inspect_networkA
  3.7/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but only states what the tool does ('Get captured network requests') and the return format. It fails to disclose critical behavioral traits such as whether this requires an active browser session, if network capturing must be enabled beforehand, potential rate limits, or error conditions. The description is minimal and misses key operational context.

  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 with a clear purpose statement followed by Args and Returns sections, using minimal sentences that each add value. It avoids redundancy and is front-loaded with the core functionality, making it easy to parse quickly.

  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 moderate complexity (network inspection), no annotations, and an output schema that defines the return structure, the description is partially complete. It covers the basic purpose and return format but lacks details on behavioral aspects like session requirements or capture mechanisms, leaving gaps for effective agent use.

  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 description adds meaningful context for the single parameter 'session' by specifying it as the 'Name of the browser session', which clarifies its purpose beyond the schema's basic string type. With 0% schema description coverage and only one parameter, this compensates adequately, though it could elaborate on session format or examples.

  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 ('Get captured network requests') and resource ('from the page'), distinguishing it from sibling tools like browser_inspect_console or browser_inspect_dom that inspect different page aspects. It precisely identifies what the tool retrieves without ambiguity.

  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 when network requests need inspection, but provides no explicit guidance on when to use this tool versus alternatives like browser_inspect_events or prerequisites. It lacks clear exclusions or comparisons with sibling tools, leaving usage context inferred rather than stated.

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

• browser_inspect_screenshotA
  3.7/5.0
  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 the output format (Base64-encoded PNG with data URI) and the full_page parameter's effect, but lacks details on permissions, rate limits, or error conditions. It adequately describes core behavior but misses advanced operational 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 well-structured with clear sections (purpose, args, returns) and uses minimal sentences. Every part adds value, though the 'Args' and 'Returns' labels are slightly redundant given the schema, but they enhance readability.

  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 moderate complexity (2 parameters, no annotations, but has output schema), the description is reasonably complete. It covers purpose, parameters, and return values, and the output schema handles return details, so no major gaps exist for basic usage.

  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?

  Schema description coverage is 0%, so the description must compensate. It explains both parameters: 'session' as the browser session name and 'full_page' controlling scrollable capture. This adds meaningful context beyond the bare schema, though it doesn't detail session format or full_page implications beyond the boolean.

  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 ('Take a screenshot') and resource ('current page'), distinguishing it from sibling tools like browser_inspect_dom or browser_inspect_text. It precisely identifies the tool's function without ambiguity.

  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 it's implied for capturing visual page states, there's no mention of prerequisites (e.g., needing an active session) or comparisons to other inspection tools like browser_inspect_network or browser_inspect_events.

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

• browser_inspect_domA
  3.9/5.0
  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: it retrieves HTML content, supports optional element selection via CSS selector, and truncates output if over 100KB. This covers the core functionality and a critical limitation (truncation), though it doesn't mention error handling, performance implications, or session state requirements.

  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: the first sentence states the core purpose, followed by structured sections for Args and Returns. Every sentence earns its place by providing essential information without redundancy, making it easy to scan and understand quickly.

  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 moderate complexity (2 parameters, no annotations, but with an output schema), the description is fairly complete. It explains what the tool does, its parameters, and a key behavioral trait (truncation). The output schema likely details the return structure, so the description needn't elaborate further. However, it could improve by mentioning session prerequisites or error cases.

  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 schema description coverage is 0%, so the description must compensate. It adds meaningful semantics: 'session' is described as 'Name of the browser session,' and 'selector' as 'Optional CSS selector to get specific element's HTML.' This clarifies the purpose of both parameters beyond their schema types (string and optional string/null). However, it doesn't provide examples or format details for the selector.

  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: 'Get DOM HTML content from the page.' This is a specific verb ('Get') + resource ('DOM HTML content') combination. However, it doesn't explicitly differentiate from sibling tools like browser_inspect_text or browser_inspect_events, which also inspect page content but for different aspects.

  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 through the mention of 'Optional CSS selector to get specific element's HTML,' suggesting it can be used for both whole-page and element-specific HTML retrieval. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like browser_inspect_text (for text content) or browser_inspect_screenshot (for visual content), nor does it mention prerequisites like needing an active browser session.

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

• browser_session_destroyA
  3.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool destroys a session and cleans up resources, which implies mutation and resource release, but lacks details on permissions needed, whether destruction is reversible, error handling, or side effects. This is a significant gap for a destructive operation.

  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: the first sentence states the purpose clearly, followed by structured Args and Returns sections. Every sentence earns its place without redundancy, making it efficient and well-organized.

  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 (destructive operation), lack of annotations, and presence of an output schema (which covers return values), the description is partially complete. It explains the action and parameter but misses critical behavioral details like safety warnings or prerequisites, leaving gaps for an AI agent.

  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 description adds meaning beyond the input schema by explaining that the 'name' parameter refers to 'Name of the session to destroy'. Since schema description coverage is 0% and there is only one parameter, this compensates well, though it could provide more context (e.g., format or examples).

  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 ('Destroy') and resource ('browser session'), distinguishing it from sibling tools like browser_session_create, browser_session_connect, and browser_session_list. It explicitly mentions cleaning up resources, which adds specificity beyond just the name.

  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 implies usage context through the action 'destroy' and resource 'browser session', suggesting it should be used when ending a session. However, it does not explicitly state when to use it versus alternatives (e.g., browser_session_connect for reusing sessions) or provide exclusions, missing full explicit guidance.

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

• browser_inspect_textA
  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 full burden. It discloses that the tool extracts text content without HTML tags, which is useful behavioral context. However, it doesn't mention potential limitations like text extraction from dynamic content, authentication requirements, or error conditions. The description doesn't contradict any annotations since none exist.

  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 structured and concise. It begins with the core purpose, then provides clear parameter explanations in a labeled 'Args' section, and concludes with return value information. Every sentence earns its place with no wasted words, and the information is front-loaded appropriately.

  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 moderate complexity (text extraction from browser), no annotations, and the presence of an output schema (which handles return values), the description is reasonably complete. It covers purpose, parameters, and basic behavior. The main gap is lack of guidance on limitations or error cases, but the output schema reduces the need to describe return format details.

  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?

  With 0% schema description coverage, the description must compensate. It provides clear explanations for both parameters: 'session: Name of the browser session' and 'selector: Optional CSS selector to get specific element's text'. This adds meaningful context beyond the bare schema, though it doesn't specify format details like CSS selector syntax examples.

  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 'Get' and resource 'text content from the page (no HTML tags)', making the purpose specific. It distinguishes from siblings like browser_inspect_dom (which includes HTML structure) and browser_inspect_screenshot (visual capture). The 'no HTML tags' clarification is particularly helpful for differentiation.

  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 through the selector parameter explanation ('Optional CSS selector to get specific element's text'), suggesting when to use this tool vs. getting all page text. However, it doesn't explicitly state when to choose this over alternatives like browser_inspect_dom or provide clear exclusion criteria for when other tools might be more appropriate.

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

• browser_session_escalateA
  4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it enables side effects, actions will be logged, and it returns a warning message with confirmation. This covers safety, auditability, and response format adequately 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 efficiently structured with a purpose statement, warning, parameter explanations, and return information in four concise sentences. Every sentence adds value, and it's appropriately front-loaded with the core functionality and warning.

  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 this is a mutation tool with no annotations, 2 parameters, and an output schema, the description is reasonably complete. It explains the tool's purpose, behavioral implications, parameters, and return value. The output schema handles return details, so the description doesn't need to elaborate further.

  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%, so the description must compensate. It documents both parameters (name and reason) with brief explanations, adding meaning beyond the bare schema. However, it doesn't provide format examples or constraints, leaving some ambiguity about parameter expectations.

  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 ('escalate') and resource ('session'), specifying that it enables action tools like click, type, and execute. It distinguishes from sibling tools by focusing on session escalation rather than direct actions or inspections, though it doesn't explicitly name alternatives.

  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 allow action tools that require escalated permissions. It implies usage before invoking tools like browser_act_click, but doesn't explicitly state when not to use it or name specific alternatives among siblings.

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

• browser_session_connectA
  4.5/5.0
  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: the session starts in 'observation-only mode' and 'actions require explicit escalation,' which are crucial for understanding permissions and safety. It also hints at the return format ('Confirmation message with session name and status'), though it could add more detail on error handling or session management.

  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 well-structured and front-loaded, starting with the core purpose, followed by behavioral notes, and then parameter and return details in labeled sections. Every sentence adds value without redundancy, making it efficient and easy to parse.

  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 complexity of browser session management, no annotations, and an output schema (implied by 'Returns' section), the description is mostly complete. It covers purpose, behavior, parameters, and returns, but could enhance completeness by mentioning prerequisites (e.g., needing an existing CDP session) or error cases, though the output schema may handle some of this.

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

  Parameters5/5

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

  The schema description coverage is 0%, so the description must compensate. It provides clear semantics for both parameters: 'name' as a 'Unique name for the session' with examples, and 'cdp_url' as a 'CDP websocket URL' with examples. This adds essential meaning beyond the bare schema, fully documenting the parameters.

  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 ('Connect to an existing browser session') and resource ('over CDP'), distinguishing it from sibling tools like browser_session_create (which creates new sessions) and browser_session_list (which lists sessions). It provides a precise technical context that differentiates its purpose.

  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 implies usage context by stating 'Sessions start in observation-only mode. Actions require explicit escalation,' which suggests this tool is for connecting to existing sessions rather than creating new ones. However, it does not explicitly compare to alternatives like browser_session_create or specify when not to use it, leaving some guidance implicit.

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

• browser_session_createA
  4.5/5.0
  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. It discloses key behavioral traits: sessions start in 'observation-only mode' (safe read state), actions require 'explicit escalation' (implying a separate permission step), and it describes the return format ('Confirmation message with session name and status'). It doesn't mention rate limits, persistence, or error conditions, but covers the essential safety and workflow context.

  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, followed by well-structured sections for Args and Returns. Every sentence earns its place: the first states the action and initial mode, the second explains escalation, and the parameter/return details are necessary given the 0% schema coverage. No wasted words.

  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 4 parameters with 0% schema coverage, no annotations, and an output schema (implied by 'Returns'), the description does well: it explains all parameters semantically and states the return format. However, for a tool that creates a session (a potentially stateful/mutating operation), it could mention more about error cases (e.g., duplicate names) or session lifecycle, though the output schema may cover some of this.

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

  Parameters5/5

  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 fully. It adds meaning beyond the schema by explaining each parameter: 'name' as a 'Unique name for the session' with examples, 'headless' as 'run browser without visible window', and viewport dimensions with defaults and units ('pixels'). This provides complete semantic context that the schema lacks.

  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 'Create' and resource 'new browser session for observation', distinguishing it from sibling tools like browser_session_connect (connect existing), browser_session_destroy (terminate), and browser_session_list (list). It specifies the session's initial state as 'observation-only mode', which is a key differentiator from action-oriented siblings.

  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: 'Sessions start in observation-only mode. Actions require explicit escalation.' This implicitly guides when to use this tool (to start a session) versus when to use escalation tools later. However, it doesn't explicitly name alternatives like browser_session_connect for reusing existing sessions or state when not to use it.

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

• browser_act_clickA
  4.6/5.0
  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. It discloses key behavioral traits: the prerequisite escalation requirement, the action's purpose (clicking), and what the return value represents ('Observed changes after the click (NOT success/failure)'). It doesn't mention potential side effects like navigation or errors, but covers essential operational context.

  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: the core purpose is stated first, followed by prerequisites, parameters, and returns in a structured format. Every sentence earns its place by providing essential information without redundancy.

  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 complexity (action with prerequisites), no annotations, and an output schema (which handles return values), the description is mostly complete. It covers purpose, prerequisites, and parameter context, but could benefit from more behavioral details like error conditions or click consequences.

  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?

  Schema description coverage is 0%, so the description must compensate. It adds meaning beyond the bare schema by explaining the 'reason' parameter ('Justification for why this click is necessary') and clarifying that 'selector' is a 'CSS selector'. However, it doesn't detail 'session' semantics or provide examples, leaving some gaps.

  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 ('Click an element on the page') and resource ('element'), distinguishing it from siblings like browser_act_type (typing) or browser_inspect_* tools (inspection). It uses a precise verb+resource combination that leaves no ambiguity about the tool's function.

  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 explicitly states when to use this tool ('REQUIRES: Session must be escalated first via browser_session_escalate'), providing clear prerequisites. It also implies when not to use it (e.g., for non-click actions like typing or inspection), though alternatives aren't named, the context is sufficient given the sibling tools list.

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

• browser_act_executeA
  4.6/5.0
  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: it requires session escalation (a critical prerequisite), executes JavaScript (implying mutation), and returns observed changes rather than success/failure (clarifying output behavior). However, it doesn't mention potential risks like script errors 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 well-structured and front-loaded with the core purpose, followed by prerequisites, args, and returns sections. Every sentence earns its place by providing essential information without redundancy, making it efficient and easy to parse.

  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 complexity (JavaScript execution with prerequisites) and no annotations, the description does well by covering purpose, prerequisites, parameters, and output behavior. The output schema exists, so return values needn't be explained in detail. However, it could mention error handling or security implications for a more complete picture.

  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?

  Schema description coverage is 0%, so the description must compensate. It adds meaningful context for all three parameters: 'session' is clarified as a browser session name, 'script' as JavaScript code, and 'reason' as a justification. This goes beyond the bare schema, though it doesn't specify format details like script syntax.

  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 ('Execute JavaScript') and the context ('in the browser context'), distinguishing it from sibling tools like browser_act_click or browser_act_type which perform different browser actions. It uses precise language that goes beyond a tautology.

  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 explicitly states when to use this tool ('REQUIRES: Session must be escalated first via browser_session_escalate'), providing clear prerequisites and distinguishing it from tools that don't require escalation. It also implies usage context by specifying it's for JavaScript execution in a browser.

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

• browser_inspect_navigateA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by explaining the operation's nature ('inspect operation'), the automatic protocol handling ('https:// added if no protocol specified'), and what gets returned ('page title and final URL after navigation'). It doesn't mention potential side effects like page loading time or navigation failures.

  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 structured with a clear purpose statement, brief explanation, and organized parameter/return sections. Every sentence earns its place, with no wasted words, and key information is front-loaded in the first sentence.

  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 tool's moderate complexity, no annotations, and the presence of an output schema (implied by the Returns section), the description is complete enough. It covers purpose, usage context, parameter semantics, and return values, providing everything needed for an agent to understand and invoke this tool correctly.

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

  Parameters5/5

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

  With 0% schema description coverage, the description fully compensates by providing clear semantics for both parameters: 'session: Name of the browser session' and 'url: URL to navigate to (https:// added if no protocol specified)'. This adds essential meaning beyond the bare 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 ('Navigate') and resource ('to a URL') with specific purpose ('for observation'). It distinguishes from siblings by explaining this is an 'inspect operation' that 'sets up what you want to observe', differentiating it from action-oriented browser tools like browser_act_click.

  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 that this is an 'inspect operation' for 'observation' setup, which implicitly suggests when to use it versus action tools. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the many sibling tools.

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

• browser_act_typeA
  4.7/5.0
  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 behavioral traits: the prerequisite escalation requirement, what the tool does (types text, optionally clears first), and what it returns (observed changes, not success/failure). It doesn't mention potential side effects like focus changes or validation triggers, but covers the essential operational context well.

  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 structured and concise: a clear purpose statement, a critical prerequisite warning, a well-organized parameter explanation, and a return value clarification. Every sentence earns its place, with no wasted words, and information is front-loaded appropriately.

  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 tool's complexity (interactive browser automation with prerequisites), no annotations, and 0% schema coverage, the description provides excellent contextual completeness. It covers purpose, prerequisites, all parameters, and return behavior. With an output schema present, it doesn't need to detail return values further, making this description complete for the tool's needs.

  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?

  With 0% schema description coverage, the description must compensate for the lack of parameter documentation in the schema. It successfully explains all 5 parameters in the Args section, providing clear semantic meaning for each (session name, CSS selector, text content, justification, clear-first flag). The only minor gap is not explaining the format for the CSS selector 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 specific action ('Type text into an input element') and resource ('input element'), distinguishing it from siblings like browser_act_click (clicking) or browser_inspect_* (inspection tools). It provides a precise verb+resource combination that immediately communicates its function.

  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 explicitly states when to use this tool: 'REQUIRES: Session must be escalated first via browser_session_escalate.' This provides clear prerequisites and distinguishes it from tools that might not require escalation, offering specific guidance on proper usage context.

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