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

With no annotations, the description must disclose behaviors. It only mentions a precondition and basic action, omitting details on overwriting existing cookies, error handling, or side effects like session modification.

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

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

The description is very concise with two sentences and front-loaded purpose. However, it could be expanded slightly without losing conciseness to improve completeness.

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

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

Given 7 parameters, no annotations, and an output schema, the description is incomplete. It does not explain parameter usage or behavioral constraints beyond the domain precondition, leaving significant gaps for an AI agent.

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

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

Schema coverage is 0% and the description adds no explanation for the 7 parameters. While schema titles provide minimal meaning, the description fails to clarify roles of optional fields like domain, secure, or session_id.

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

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

Clearly states 'Add a cookie' with a verb and resource. The precondition about domain distinguishes it from sibling tools like get_cookies and delete_cookie.

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

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

Provides a precondition (browser must be on page from domain) but does not give explicit guidance on when to use or avoid this tool compared to alternatives like delete_cookie or get_cookies.

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

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

With no annotations provided, the description fails to disclose important behavioral details: it does not mention that the tool synchronously handles the dialog, closes it on accept/dismiss, or throws an error if no dialog is present. Actions like send_text are not explained in terms of preconditions.

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

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

The description is concise (one sentence) and front-loaded with the core purpose, followed by a list of actions. It avoids fluff, though it could be slightly more structured to separate parameter descriptions.

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

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

Given three parameters and no annotations, the description is too brief. It lacks operational context such as preconditions (dialog must be present), behavior on success/failure, and specifics about each action. The output schema exists, shifting the burden for return values, but the description still needs more detail for safe usage.

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

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

Schema coverage is 0%, so the description must compensate. It lists possible values for the 'action' parameter, adding meaning. However, it does not describe the 'text' parameter (used with send_text) or 'session_id', providing only partial guidance.

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

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

The description clearly states that the tool 'Handle browser alert/confirm/prompt dialogs' and lists specific actions ('accept, dismiss, get_text, send_text'), making the purpose unambiguous and distinguishing it from sibling tools like click, open_page, or type_text.

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

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, such as after a dialog appears or how to handle different dialog types. The description simply lists actions without context.

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

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

With no annotations, the description carries full burden but only states the core behavior. It omits critical behavioral traits such as whether it waits for element visibility, scrolls into view, or throws an error if the selector is not found.

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

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

The description is a single, front-loaded sentence with no filler. It is appropriately concise for a straightforward click action.

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

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

Despite having an output schema, the description does not mention return values or side effects. It lacks context about error handling, waiting behavior, or how it interacts with the page state, which is important for an agent to invoke it correctly.

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

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 implicitly clarifies that 'selector' is a CSS selector, but it does not mention the 'session_id' parameter at all, leaving its purpose unexplained.

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

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

The description clearly states the action ('Click') and the target ('DOM element by CSS selector'). It effectively distinguishes from sibling tools like 'type_text' or 'press_key' by specifying the click action and selector-based targeting.

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

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

No usage guidance is provided. The description does not indicate when to use this tool over alternatives (e.g., 'press_key' for keyboard clicks, or when an element might need scrolling or waiting).

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

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

No annotations are provided, and the description fails to disclose any behavioral traits, such as whether closing is destructive, idempotent, or affects other sessions. The agent receives no information beyond the action itself.

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

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

The description is a single, short sentence with no waste. However, it is under-specified for the tool's role, making it adequate but not efficient in conveying necessary information.

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

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

Given the simple tool with one parameter and no output schema details in the description, the description is incomplete. It does not mention return values or side effects, 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.

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 does not explain the meaning of 'session_id' or provide any additional context beyond what the schema already shows.

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

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

The description uses a specific verb 'close' with resource 'browser session' and mentions the method 'by ID'. It clearly distinguishes from sibling tools like create_session and list_sessions.

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

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

No guidance on when to use this tool versus alternatives (e.g., when to close a session, what prerequisites exist). The description does not mention any context for usage.

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

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

With no annotations, the description carries full burden. It only states default browser and headless mode but does not disclose potential side effects, authentication needs, rate limits, or what happens if parameters are invalid.

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

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

Single sentence is efficient and front-loaded. However, given the lack of other details, slightly more context would be beneficial without harming conciseness.

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

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

Given 2 optional parameters and an output schema, the description lacks detail about return value, session lifecycle, and how this tool fits with siblings like close_session or get_session_info.

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

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. While it implies browser parameter values and headless meaning, it does not clarify valid inputs (e.g., browser names) or the effect of changing defaults.

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

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

Description clearly states the verb (create) and resource (browser session), and specifies default behavior (Chrome headless). It distinguishes itself from sibling tools that perform other actions like clicking or navigating.

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

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

No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or provide context for when a new session is needed over using existing ones.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only states deletion but does not explain side effects, permissions needed, or the effect of omitting the name parameter. The session_id parameter is not addressed.

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

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

The description is very short at two sentences, but it lacks necessary detail to be fully informative. Conciseness is achieved at the expense of completeness.

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

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

Given the tool has two parameters and an output schema, the description is insufficient. It does not explain the role of session_id or the behavior when name is null. The tool's complexity is low, but the description still misses key context.

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

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

Schema coverage is 0%, meaning the description adds little beyond the schema. It hints at the 'name' parameter by mentioning deletion by name but does not explain null behavior or the purpose of session_id. The description fails to compensate for missing schema documentation.

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

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

The description clearly states it deletes cookies, specifying it can delete all or a specific one by name. This distinguishes it from sibling tools like add_cookie and get_cookies. However, it omits the session_id parameter, slightly reducing clarity.

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

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

There is no guidance on when to use this tool versus alternatives like clearing cookies via open_page or other methods. No preconditions or postconditions are mentioned.

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

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

No annotations are provided, so the description should disclose behavioral traits. It only states 'return the result' without specifying execution blocking, security context, or error behavior. This leaves the agent uninformed about important aspects.

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

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

The description is a single sentence, which is concise but lacks depth. It earns its place by stating the core function, but omits crucial details, making it minimally acceptable rather than well-structured.

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

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

Given the presence of an output schema, the description need not detail return values, but it should explain execution context (e.g., synchronous, global scope). With no annotations and incomplete parameter info, the description is insufficient for an agent to fully understand the tool.

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

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

The description adds no meaning beyond the input schema. The 'script' parameter remains undefined (e.g., syntax, format), and 'session_id' is not explained. With 0% schema description coverage, the description should compensate but fails.

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

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

The description clearly states the action 'Execute JavaScript' and the target 'in the browser', and it differentiates from sibling tools like click, type_text, etc., which perform specific UI actions rather than arbitrary script execution.

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

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 or any prerequisites. It does not mention any limitations or conditions for use.

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

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

No annotations are provided, so the description must cover behavioral traits. It only mentions two actions without explaining their effects, prerequisites, or error states. For example, what happens if the specified frame does not exist? This is insufficient for a tool that manipulates browser context.

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

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

The description is very concise (two sentences) and front-loaded with the core purpose. It could benefit from listing actions in a structured way, but overall it is efficient and avoids unnecessary text.

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

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

Given the tool has 3 parameters, 1 required, and an output schema, the description is incomplete. It does not explain return values, error handling, or how to use the identifier parameter effectively. With no annotations, the description should provide more context for correct invocation.

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

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

Schema description coverage is 0%, meaning param descriptions are missing. The tool description adds only the hint of 'switch' and 'default' for the action parameter but does not explain the 'identifier' parameter (e.g., how to specify a frame by index or name) or 'session_id'. This is minimal compensation for lack of schema descriptions.

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

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

Description clearly states the purpose: switching focus to a frame or back to main page. It specifies actions ('switch', 'default'), which helps identify the resource. However, it does not differentiate from sibling tools like 'window' or 'alert', though the frame concept is unique.

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

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

Description implies usage context: when you need to interact with a frame. It does not explicitly state when not to use or mention alternatives. The sibling list includes no other frame-specific tools, so the guidance is adequate but not explicit.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only states it 'gets' a value, implying a read operation, but fails to mention behavior on missing elements, error handling, or whether it waits for the element.

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

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

The description is a single, front-loaded sentence with an example in parentheses. No fluff or redundant information.

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

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

The description is minimal given the complexity of 3 parameters and no annotations. It lacks details on return value, error behavior, and the role of the optional session_id. Output schema exists but is not described.

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

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

Schema coverage is 0%, so the description must add meaning. It provides examples for the 'attribute' parameter but does not clarify 'selector' (CSS selector? XPath?) or 'session_id'. Partial compensation.

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

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

The description clearly states it retrieves an attribute value from a DOM element and provides concrete examples (href, value, class), making its purpose specific and distinguishable from siblings like get_text.

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

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

No guidance is given on when to use this tool versus alternatives (e.g., get_dom, get_text). There is no mention of context, preconditions, or exclusions.

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

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

No annotations; description fails to disclose behavioral traits such as whether logs are cleared on retrieval, read-only nature, or session requirements. 'Captured' is vague.

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

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

Single concise sentence, front-loaded with key information, but lacks necessary details about parameters and behavior.

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

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

Despite having an output schema, the description omits parameter semantics and behavioral context. With many sibling tools, more specificity is needed for effective selection.

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

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

Schema description coverage is 0%. Description does not mention the session_id parameter, leaving its purpose and usage entirely unexplained.

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

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

Description clearly states verb 'Return' and resource 'captured browser console log entries', distinguishing it from siblings like get_network_logs and get_dom.

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

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

Implies usage for retrieving console logs but provides no explicit when-to-use, prerequisites, or exclusions. Sibling tools exist but no alternatives mentioned.

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

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

No annotations provided, so description carries full burden. It only states basic return behavior (all or specific), with no disclosure of idempotency, permissions, side effects, or rate limits.

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

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

Extremely concise with two sentences, front-loaded with verb. No unnecessary words.

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

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

Given sibling tools like create_session and list_sessions, the omission of session_id parameter is a significant gap. Output schema exists but description doesn't hint at return format or session context.

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

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

Schema description coverage is 0%, but description only explains 'name' parameter (filter by name). The 'session_id' parameter is entirely unmentioned, leaving its purpose unclear.

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

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

Clearly states verb 'Get' and resource 'cookies', distinguishes between retrieving all or a specific one by name. Could improve by noting session context, but sufficient among siblings.

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

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

No guidance on when to use this tool versus alternatives like get_dom or get_text. Agent must infer from tool name alone.

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

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

With no annotations, the description carries full burden for behavioral disclosure. It implies a read-only operation but does not mention potential side effects, performance implications, or that it returns the current DOM state after JavaScript execution.

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

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

The description is a single front-loaded sentence with no wasted text. However, it is overly terse, lacking essential context that could be added without harming conciseness.

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

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

Given the output schema exists, the description need not cover return values, but it fails to explain the meaning of 'full page HTML source' or the optional session_id. The context is insufficient for an agent to use the tool correctly.

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

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

The schema has 0% parameter description coverage and the description does not mention the session_id parameter at all. No additional meaning is provided beyond the raw schema.

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

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

The description clearly states the tool returns the full page HTML source, with a specific verb and resource. It distinguishes from siblings like get_text or screenshot, but could be more precise about whether it includes dynamic content.

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

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

No guidance on when to use this tool versus alternatives such as get_text or execute_js. The description lacks context on prerequisites, use cases, or exclusions.

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

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

With no annotations, the description carries full burden. It uses the vague term 'captured' without explaining how logs are captured, whether retrieval is destructive, or if logs are cumulative. Key behavioral traits are missing.

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

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

The description is a single sentence, making it concise, but it is too vague and lacks essential details. It could be more informative without sacrificing brevity.

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

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

Given the complexity (optional parameter, no annotations) and the existence of an output schema (though not shown), the description omits critical context about preconditions, behavior, and parameter semantics, making it incomplete.

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

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

Schema description coverage is 0%, and there is one parameter (session_id). The description does not explain the parameter's purpose, default behavior, or valid values, leaving the agent without necessary context.

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

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

The description states the tool returns all captured network request/response entries. The verb 'return' and the resource 'network request/response entries' are specific, and it distinguishes from sibling tools like get_console_logs which returns console logs.

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

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

No guidance on when to use this tool versus alternatives, nor does it mention prerequisites like whether network capture must be enabled (e.g., via intercept_requests). The usage context is entirely implied.

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

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

The description only states that it returns data, implying a read-only operation, but provides no behavioral details such as whether it requires a session, how it handles errors, or what happens if no metrics are available. With no annotations, the description carries the full burden and falls short.

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

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

The description is a single sentence, which is concise and front-loaded, but it is arguably too minimal. While it avoids verbosity, it sacrifices necessary detail, earning a middle score.

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

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

The tool has an output schema (not shown), which reduces the burden to describe return values. However, the lack of parameter documentation and usage guidance leaves gaps. For a simple tool with one optional param, the description is barely adequate.

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

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

The single parameter 'session_id' has no description in the schema (0% coverage) and the tool's description does not mention it at all. The agent receives no information about when or why to provide a session ID, making the parameter effectively opaque.

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

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

The description clearly states the tool returns 'page performance timing data', which distinguishes it from siblings like get_network_logs or get_console_logs that return different data types. However, it lacks specificity about what timing metrics are included (e.g., load time, first paint), preventing a score of 5.

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

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. For example, it doesn't clarify that this tool is for performance metrics rather than network logs or DOM state, leaving the agent without decision support.

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

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

Without annotations, the description should disclose behavioral traits. It only says 'Get metadata' but does not explain what metadata is returned (e.g., user agent, screen size) or if there are side effects. The existence of an output schema is not mentioned.

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

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

The description is very concise with one sentence, but it lacks necessary details. While it is not verbose, the brevity sacrifices informative content.

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

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

Given zero annotations and one optional parameter, the description is too thin. It does not mention the output schema's structure or provide context on typical use cases, leaving the agent with insufficient information.

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

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

The input schema has 0% description coverage, and the description offers no explanation of the 'session_id' parameter. It is unclear what behavior occurs when the parameter is null (likely current session) vs a string value.

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

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

The description clearly states the verb 'Get metadata' and the resource 'browser session', making the tool's purpose unambiguous. It distinguishes from sibling tools like 'close_session' and 'list_sessions'.

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

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 'list_sessions' or when to specify a session_id vs leaving it null. The description lacks context for appropriate invocation.

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

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

The term 'visible inner text' indicates that only visible text is returned, which is a behavioral trait beyond a simple read. However, it does not disclose behavior on missing elements, timing, or error handling. With no annotations, additional context would be beneficial.

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

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

The description is a single sentence of 8 words, extremely concise and front-loaded. Every word is essential and no filler exists.

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

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

Given the low complexity of the tool and the existence of an output schema, the description covers the core action. However, it lacks parameter guidance and usage context, which is needed due to zero schema coverage.

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

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

Schema description coverage is 0%, yet the description adds no information about the two parameters (selector and session_id). The description does not explain what selector is or how session_id affects the call, leaving the agent to rely solely on parameter names.

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

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

The description 'Get the visible inner text of an element' uses a specific verb (get) and resource (visible inner text of an element). It clearly distinguishes from sibling tools like get_attribute (attribute vs text) and get_dom (DOM structure vs text).

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

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

No guidance on when to use this tool versus alternatives like get_attribute or execute_js. The description implies it's for visible text, but does not explicitly state that other tools are better for hidden text or attributes.

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

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

With no annotations, the description must disclose behavioral traits. It mentions 'intercept' and actions but does not explain the effect on network traffic, how to stop interception, or side effects. The description is insufficient.

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

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

The description is a single sentence, front-loading the core action. It is concise, though could add more detail without becoming verbose.

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

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

Given 3 parameters with no schema descriptions, no annotations, and the tool's moderate complexity, the description is incomplete. It does not explain the output (despite output schema existing), how to use, or constraints. Sibling tools add context but the description itself is lacking.

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

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 mentions 'pattern' and 'log or block' but does not describe pattern format, valid action values (beyond defaults), or session_id usage. Parameter semantics are vague.

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

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

The description clearly states the tool registers a URL pattern for network interception with log or block actions. It uses a specific verb-resource pair and distinguishes from sibling tools that perform other browser actions.

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

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

No guidance on when to use interception vs. other network tools, or when to choose log over block. The description lacks context for usage decisions.

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

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

Since no annotations are provided, the description carries full burden for behavioral disclosure. It only states the tool lists sessions, implying a read-only operation, but does not explicitly confirm lack of side effects, authentication requirements, or rate limits. Minimal transparency.

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

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

The description is extremely concise (6 words) and front-loaded. Every word is necessary; there is no fluff or repetition. Ideal for a simple tool with no parameters.

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

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

Given the tool's simplicity (no parameters, output schema present), the short description is largely adequate. However, it could benefit from defining 'active' or listing typical output fields like session ID or URL. The presence of an output schema reduces the burden.

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

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

With zero parameters and 100% schema coverage, the description has no additional meaning to add. The baseline score of 4 is appropriate as the schema already fully describes the interface.

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

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

The description uses a specific verb 'list' and clearly identifies the resource as 'active browser sessions'. It effectively distinguishes from sibling tools like 'create_session' and 'close_session' by focusing on enumeration. No ambiguity.

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

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 does not mention when not to use it or contrast with similar tools like 'get_session_info' for detailed session data. The agent receives no decision-making context.

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

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

No annotations provided. Description fails to disclose what happens if browser history is empty, whether navigation affects session state, or any side effects of the action.

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

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

Very short sentence, but it omits essential information about parameters. Conciseness is acceptable for the purpose but at the cost of completeness.

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

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

Given the tool's simplicity, the description is still insufficient. It lacks parameter documentation and behavioral details that would help an agent use it correctly.

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

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

The only parameter 'session_id' is not mentioned in the description. With 0% schema description coverage, the description must compensate but does not. Agent has no clue what session_id is for.

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

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

Clearly states the verb 'Go back' and the resource 'browser history'. Effectively distinguishes from sibling tool 'navigate_forward'.

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

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

No guidance on when to use this tool vs alternatives like 'navigate_forward'. No context about prerequisites or typical scenarios.

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

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

No annotations are provided, and the description fails to disclose key behavioral traits: what happens if there is no forward history (error or no-op), does it wait for page load, or how it affects session state. This is a critical gap for a navigation action.

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

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

The description is a single sentence with no wasted words, but it lacks any structural formatting (e.g., bullet points or sections) that could improve readability for an AI agent.

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

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

Given the tool's simplicity (1 optional param, output schema present), the description should at minimum mention the session_id parameter and the return value or behavior. It fails to do so, leaving the context incomplete.

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

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

The schema has one optional parameter (session_id) with 0% schema description coverage. The description does not explain the parameter's purpose, leaving the agent without guidance on whether it is needed or how to use it.

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

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

The description clearly states the action ('go forward') and resource ('browser history'), effectively distinguishing it from siblings like navigate_back and open_page. However, the verb 'go' is generic and could be more precise, e.g., 'navigate forward'.

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

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

No guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., must have forward history), nor does it direct the agent to navigate_back or open_page for other navigation tasks.

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

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 does not disclose behavioral traits such as whether it waits for page load, handles redirects, or error conditions.

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

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

The description is a single concise sentence, but it lacks any structure or elaboration. It is not overly verbose but also not sufficiently informative.

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

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

Given the simple nature of the tool, the description is somewhat adequate but misses important context regarding session handling and the output schema. It could be more complete.

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

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

Schema description coverage is 0%, and the description adds no meaning to the parameters. It does not explain the url format, protocols, or the role of session_id.

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

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

The description clearly states the verb 'Navigate' and the resource 'browser to a URL', which distinguishes it from sibling tools like navigate_back and navigate_forward.

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

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 such as navigate_back or navigate_forward, nor any prerequisites or context for usage.

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

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

No annotations provided. Description does not disclose effects on UI, event triggering, or behavior for invalid keys. Minimal 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.

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

Extremely concise, two sentences, front-loaded with key information. No redundant phrasing.

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

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

Despite having an output schema, return values are not described. The tool has 3 parameters with no full explanation for two of them. Lacks examples and usage context for completeness.

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

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

Schema description coverage is 0%, so description must compensate. Only the 'key' parameter gains context via examples. 'selector' and 'session_id' are undefined. Lacks format details for key names.

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

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

Description clearly states the action ('press a keyboard key'), provides examples (Enter, Tab, Escape), and mentions optional element targeting. This distinguishes it from typing or clicking siblings.

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

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

No guidance on when to use this tool versus alternatives like type_text or click. No exclusions or context for appropriate usage.

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

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

With no annotations, the description should fully disclose behavioral details, but it only states the capture action. It does not mention that the tool requires an existing session, the nature of the output, or error conditions.

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

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

The description is a single, well-structured sentence with no redundant words, and it places the key verb 'Capture' upfront.

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

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

Given the 0% parameter description coverage, the description should compensate by explaining the parameter and usage context. It does not, leaving the agent with incomplete information for correct invocation.

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

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

The single parameter session_id is not explained in the description, and the input schema provides no description (0% coverage). The agent has no clues about how to use or omit this parameter.

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

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

The description clearly states the action (capture), the output format (base64-encoded PNG), and the scope (current viewport), effectively distinguishing it from sibling tools like get_dom or get_text.

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

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

No guidance on when to use this tool versus alternatives, no prerequisites (e.g., active session), and no exclusion criteria are provided.

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

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

With no annotations, the description must disclose behavioral traits. It states the tool clears the input before typing, which is a key behavior. However, it does not specify error handling, waiting behavior, or whether the selector must be visible.

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

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

The description is a single sentence with no wasted words. It is appropriately front-loaded, though slightly terse.

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

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

Given the complexity of browser automation tools and the existence of an output schema, the description lacks details on return values, error states, and preconditions. It does not explain behavior when the element is not found.

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

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

Schema description coverage is 0% and the description adds no information about parameters. The agent is left without hints for 'selector' (CSS/XPath?), 'text' (format?), or 'session_id'.

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

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

The description uses a specific verb ('type') and resource ('text into it') and clearly distinguishes from sibling tools like 'click' or 'press_key' by stating it clears the input first.

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

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

No guidance on when to use this tool versus alternatives such as 'press_key' or 'execute_js'. The description does not mention prerequisites or context, leaving the agent to infer usage.

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

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

Annotations are absent, so the description must bear the full burden. It only states 'wait until visible' without disclosing polling behavior, timeout outcomes, scrolling, or error handling.

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

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

Single front-loaded sentence with no unnecessary words. Efficient.

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

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

An output schema exists, reducing need for return value explanation. However, missing details on timeout behavior and parameter units make it less than fully complete.

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

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

Schema description coverage is 0%, and the description does not elaborate on parameter meanings beyond the implied selector. Timeout unit and session_id usage are unstated.

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

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

The description clearly states the verb 'Wait' and the resource 'CSS selector visible on the page'. It distinguishes from sibling tools like wait_for_dom_stable, which waits for DOM stability, and other navigation/action tools.

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

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

No guidance on when to use this tool versus alternatives such as wait_for_dom_stable or other waiting strategies. No prerequisites or context provided.

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

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

No annotations exist, so the description alone must convey behavior. It mentions 'smart wait' but does not explain polling, mutation detection, timeout behavior, 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.

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

The description is a single concise sentence, which is front-loaded, but it sacrifices necessary parameter and behavioral details.

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

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

Given the tool's moderate complexity, the description lacks parameter explanation and usage context, even though an output schema exists (not shown). It is insufficient for correct agent invocation.

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

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

With 0% schema description coverage, the description should explain parameters. It does not mention 'timeout' (default 5 but unit unclear) or 'session_id', leaving the agent uninformed.

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

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

The description clearly states the verb 'wait' and the resource 'DOM stops mutating', and specifies it's for AJAX content, distinguishing it from the generic sibling 'wait_for'.

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

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

The description implies usage for dynamic pages with AJAX, but does not explicitly state when to use this tool versus alternatives like 'wait_for' or 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.

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

With no annotations, the description must disclose behaviors. It only lists actions without explaining side effects (e.g., does 'close' close a window or a tab? Does 'switch_latest' focus the most recent window?). The description is too terse to provide transparency.

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

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

The description is very short (one sentence) and front-loads the purpose. However, it omits critical details, making it under-specified rather than efficiently concise.

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

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

Given 4 parameters (1 required), an output schema, and no annotations, the description is incomplete. It does not explain how parameters relate to actions, valid action values, or expected outputs, insufficient for reliable tool invocation.

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

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

Schema description coverage is 0%, yet the description adds no meaning for the parameters (action, handle, index, session_id). It only lists actions but does not explain parameter usage. An agent cannot infer valid values or required combinations from this description.

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

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

The description clearly states the tool manages browser windows and tabs and lists the available actions, making the purpose understandable. However, it lacks specificity on what each action does, and does not differentiate from sibling tools (e.g., open_page, navigate_back) which also involve window/tab context.

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

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

No guidance on when to use this tool vs alternatives. For example, when to use this tool's 'switch_latest' versus simply opening a new page. The description does not provide context or examples.

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