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

No annotations are provided, so the description must carry the full burden. It fails to disclose behaviors such as failure when no history exists, async behavior, or side effects (e.g., losing form state).

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. It is appropriately sized for a simple no-parameter tool.

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?

For a simple browser action with no parameters and no output schema, the description is adequate but lacks details on edge cases (e.g., no history) and return behavior. It meets minimum viability.

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 tool has zero parameters, so no parameter documentation is needed. The description adds no extra meaning, but baseline for 0 params is 4.

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 '浏览器后退一页' (browser go back one page) clearly states the action and distinguishes it from siblings like 'forward' and 'navigate'. It specifies the scope (one page), making it unambiguous.

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 vs alternatives like 'forward' or 'reload'. The agent must infer usage from the name alone, which is insufficient for optimal tool selection.

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 fails to disclose behavioral details like visibility requirements, error handling, 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?

Description is a single, efficient sentence with no unnecessary words, achieving maximum 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?

Lacks return value or behavioral details, but given low complexity and schema richness, it is minimally 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?

Schema coverage is 100% and descriptions are clear. The tool description adds no additional meaning beyond what is already in the input 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?

Description clearly states the tool checks or unchecks checkboxes/radio buttons, which is specific and distinguishes from siblings like click or select.

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 (e.g., click, select). The context is implied but lacks exclusions or prerequisites.

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 states 'click' and mentions timeout and selector, implying waiting behavior. However, it does not disclose if the tool waits for the element to be clickable, what happens on failure, or return behavior.

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 with no wasted words. It provides essential information efficiently.

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 no output schema and simple tool, the description lacks details on error handling, return values, and behavior with multiple matches. The index parameter hints at multiple matches but is not explained.

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 100%, so baseline is 3. The description adds no value beyond what the schema already provides for each parameter. It mentions 'CSS selector or element index' which mirrors the parameters.

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 clicks elements on the page using CSS selectors or index. It distinguishes from sibling tools like hover, fill, or check, but does not elaborate on edge cases like double-click or right-click.

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., hover, check). No mention of prerequisites like page load or element visibility.

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 present, so the description must fully disclose behavior. It states the tool closes the browser and releases resources, but does not mention side effects like data loss, irreversibility, or that the session ends. More detail is needed for a destructive 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 extremely concise (two short sentences) with no wasted words. It front-loads the action 'close browser'.

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?

For a simple zero-parameter tool, the description is minimally adequate but could be more complete by stating that the browser session ends and must be re-launched for further interactions. It lacks context about post-close state.

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?

There are no parameters, and schema description coverage is 100% trivially. Per guidelines, 0 params yields a baseline of 4, and the description adds no unnecessary param info.

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 'close browser, release resources', specifying the action and target. Among siblings like 'back', 'navigate', 'click', this is the only tool for closing the browser, so purpose is distinct.

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 (e.g., when finished with the browser) or alternatives. The agent must infer context from the 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?

在没有注释的情况下，描述主动披露了清空现有内容这一行为特征，但对错误处理或返回值未提及。

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?

一句话说明核心功能，无冗余信息，关键行为前置。

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?

作为简单操作工具，描述基本完整（动作+行为），但缺少返回值说明和错误处理上下文。

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已覆盖所有参数并给出描述，描述未额外增加参数层面的语义，仅泛化了清空行为。

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?

明确的动词+资源（填入文本到输入框），并附带副作用描述（会先清空内容），与兄弟工具（如click、hover）明显区分。

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?

描述隐含了用于输入框的场景，但没有明确的使用时机、排除条件或替代工具（如click后输入）。

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 carries the full burden of behavioral transparency. It only states the action and does not disclose behavior such as whether it fails silently if no forward history exists, or whether it relies on browser session state. This is minimal disclosure for a simple tool.

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 of five characters. It is maximally concise and conveys the essential information with no wasted 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?

For a simple one-action tool with no parameters and no output schema, the description is adequate but could be more informative given the sibling context (e.g., mentioning it uses browser history navigation as opposed to 'navigate'). It provides minimal context beyond the action itself.

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?

There are no parameters (schema coverage is 100% trivially). Since no parameters exist, the description does not need to add parameter meaning. Baseline score of 4 is appropriate.

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 '浏览器前进一页' clearly states the action (forward) and the resource (browser page). It effectively distinguishes from the sibling 'back' tool, which performs the reverse action.

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 guidelines are provided. The description does not specify when to use this tool over alternatives like 'navigate' or 'back', nor does it mention prerequisites (e.g., must have forward history).

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 carries full burden but only states what it does. It does not disclose side effects, required permissions, or behavior in edge cases (e.g., no inputs on page). As a read operation, it is not explicitly marked as non-destructive, and the return format is only briefly 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 a single clear sentence that is front-loaded with the action. It is concise with no superfluous 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?

For a tool with no parameters, the description covers the essential purpose and return value. However, lacking an output schema, it could be more explicit about the format of returned references and names. The context signals show it is one of many browser automation tools, so additional usage context would be helpful but not critical.

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?

There are no parameters, so schema coverage is trivially 100%. Baseline for 0 parameters is 4; the description does not need to add parameter info, and it does not.

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 gets all inputable form elements (input, textarea, select) and returns their references and names. This distinguishes it from sibling tools like get_links and get_text, which have different purposes.

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

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention coexistence or prerequisites, leaving the agent to infer usage from the clear purpose.

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 states the tool returns URL and link text but does not disclose behavioral traits such as whether it only works on the current page, if it ignores hidden links, or how it handles pagination or iframes. The description is minimally adequate for a simple read tool.

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 that efficiently conveys the tool's purpose and output. No wasted 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 the tool's simplicity (2 parameters, no output schema), the description adequately covers functionality. It specifies the return fields (URL and link text), though it could benefit from a brief note on the return format (e.g., array of objects). Overall, it is sufficiently complete for an agent to understand the tool's purpose.

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 100%, so baseline is 3. The description does not add meaning beyond the schema; it simply restates that the tool retrieves links. Parameters maxItems and selector are already well-documented in the 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 retrieves all links (<a> tags) on the page and returns their URLs and text. It distinguishes itself from sibling tools like get_text and get_inputs by specifying the resource (links) and output (URL and link 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?

The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions or provide context for selection among siblings such as search or get_text.

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 burden. It discloses the core behavior (extract text, remove HTML) but does not cover other aspects like read-only nature or formatting of output.

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 with two short sentences, front-loaded with the core purpose, and no wasted 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?

Despite lacking an output schema, the description is fairly complete for a simple extraction tool. It could mention that it works on the current page or the output format, but it is sufficient given the tool's simplicity.

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 100% (both parameters described well). The description adds minor confirmation about full text vs CSS selector, but adds limited value beyond the 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 extracts plain text from a page, removing HTML, and supports both full text and CSS selector scope. It distinguishes from siblings like get_inputs and get_links.

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 text extraction but does not provide explicit guidance on when to use this tool versus alternatives 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?

No annotations are provided, so the description fully carries behavioral disclosure. It states the effect (hover), but does not disclose aspects like scrolling into view, waiting for transitions, or any side effects. It is adequate but minimal.

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

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

A single, concise sentence with no superfluous words. Every part is necessary.

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 simplicity of the tool (one parameter, no output schema), the description is mostly adequate but lacks completeness regarding preconditions (element visibility, existence) and possible outcomes.

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 100% and the parameter 'selector' is described as 'CSS 选择器'. The description does not add extra meaning beyond the schema, warranting the baseline of 3.

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: hovering over an element with a CSS selector, and provides an example of triggering a dropdown menu. It effectively distinguishes from sibling tools like click or scroll.

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 when to use (to trigger hover effects), but it lacks explicit guidance on when not to use or alternatives among the many sibling tools. No prerequisites or fallbacks 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 provided, so the description must disclose behavioral aspects. It only mentions launch modes but omits side effects (e.g., creates new instance), required permissions, or whether it can fail. Contrast with 'Creating a new record' tools which would need such 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 a single sentence, concise. However, it could include more critical context without becoming verbose, so it is good but not perfect.

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?

For a launch tool with two parameters and no output schema, the description covers the basic action but does not address return values, readiness confirmation, or failure states. Adequate but not 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 coverage is 100%; both parameters have descriptions. The tool description restates the headless option but adds no new semantic depth beyond the schema. Baseline 3 is appropriate.

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 launches a browser and specifies the two modes (headless/headed). It is a specific verb-resource pair and distinguishes itself from sibling navigation/interaction 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?

The description implies the tool is the starting point for browser automation but does not explicitly state when to use it (e.g., before other tools) or when not to (e.g., if browser already running). 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?

With no annotations provided, the description carries the full burden. It does not disclose behavioral traits such as state changes, history manipulation, or prerequisites. It only states that it supports any website. The schema hints at loading behavior via waitUntil, but the description lacks explicit safety or side-effect information.

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?

Two sentences, front-loaded with the core purpose ('导航到指定 URL') and concise use cases. No redundant or extraneous 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?

For a simple navigation tool with well-described parameters, the description is complete enough to cover main use cases. However, it could mention prerequisites (e.g., browser must be launched) or side effects (adds to history), but these are not critical given the 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 100% with good parameter descriptions (url format, timeout default, waitUntil enum). The description does not add extra meaning beyond what the schema provides, so a baseline score of 3 is appropriate.

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 navigates to a specified URL and supports any website, with specific use cases like opening pages or redirecting after clicking. This distinguishes it from sibling tools like back, forward, and reload, but lacks explicit differentiation from 'launch' which initializes the browser.

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 gives context ('可用于打开网页、点击链接后的跳转') implying when to use it (opening pages, after link clicks), but does not explicitly state when not to use it or provide alternatives among the sibling tools.

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 fully bears the burden. It only says 'refresh current page' without disclosing behavioral traits like whether it discards unsaved data, triggers network requests, or affects page history. 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?

Single sentence, front-loaded with the action. Minimal and to the point. However, it is in Chinese which may reduce clarity for English-only agents, but conciseness is high.

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 simplicity (no parameters, no output schema), the description is adequate but could be improved by noting effects like page state reset. It provides the core action but lacks completeness for a tool with sibling tools that have richer descriptions.

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 adds no param details, which is acceptable since there are none. Baseline score of 4 because no additional value needed.

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 '刷新当前页面' means 'refresh the current page', which is a clear and specific verb-resource pair. It distinguishes from siblings like back, forward, and navigate. However, it is a tautology of the tool name 'reload' but adds the context of 'current page'.

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 reload versus alternatives like navigate or wait_for_url. No exclusions or context provided. The description simply states the action without usage advice.

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 must fully disclose behavior. It mentions capture modes but omits critical details: what happens if both fullPage and selector are set?, file format, overwrite behavior, return value (if any), error handling. The brief description fails to convey the tool's complete behavioral profile.

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 concise single sentence, front-loading the main verb and listing options. No wasted words, but may be too brief for a tool with three parameters and potential interactions.

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 output schema, the description adequately covers the main functionality but lacks explanation of parameter interaction (e.g., how to achieve each mode via specific parameter settings) and does not mention return value or side effects.

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 100%, so baseline is 3. The description adds grouping of modes but does not provide additional semantics beyond the schema. For example, it doesn't clarify parameter precedence or how to combine path with other parameters.

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 tool captures screenshots of a page, listing three modes (full page, element, visible area). This differentiates it from sibling tools which are all navigation or interaction actions. However, it does not explicitly contrast with potential overlapping tools (none in siblings) or provide deeper specificity.

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 when to use each mode (fullPage for full scroll, selector for element, none for visible area), but does not provide explicit guidance on when not to use or alternatives. No discussion of prerequisites, file path handling, or conflict resolution between parameters.

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?

Description claims ratio scrolling but schema only has pixel and element, creating inconsistency. No side effects or limitations disclosed.

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 concise but introduces inconsistency, so not optimally 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?

Lacks details on how selector works, what ratio means, and output behavior. Incomplete given the tool's complexity and lack of output schema.

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 has 100% coverage, but description introduces concept of 'ratio' not present in schema, causing confusion. Does not add value beyond 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?

Description clearly states the tool scrolls the page and lists different methods (pixel, element, ratio). However, it does not distinguish from sibling tools like back, forward, navigate which are also about movement.

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 scrolling vs navigation tools. Missing context on prerequisites or alternatives.

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 mentions highlighting and returning positions, but does not disclose whether it is read-only, if it scrolls to matches, or if there are side effects. Adequate but lacking depth.

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 that efficiently conveys purpose, behavior, and output. 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?

For a simple tool with 2 parameters and no output schema, the description is fairly complete: it specifies the action, the result (highlights and positions), and the analogous browser behavior. However, it does not detail the format of position information or whether it handles multiple matches.

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 100% (both parameters have descriptions). The tool description adds context (Ctrl+F behavior) but does not enhance parameter meaning beyond the schema. Baseline 3 is appropriate.

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's purpose: searching text on a page (Ctrl+F behavior), highlighting matches, and returning position information. It uses a specific verb ('search') and resource ('page'), and is distinct from sibling tools like click or fill.

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 finding text on a page, but does not explicitly state when to use this tool versus alternatives (e.g., get_text for extracting all text, scroll for navigation). No 'when not to use' guidance is 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 carries full burden but only says 'select option' without disclosing side effects (e.g., change events, multiple selection support, error handling). Minimal behavioral disclosure.

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?

One concise sentence, front-loaded with core action. No wasted words, but could be slightly more structured with separate sections.

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?

For a simple tool with schema covering parameters, the description is minimally complete. Lacks details on selector expectations or behavior with multiple select elements.

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 covers both parameters (100% coverage). Description adds no extra meaning beyond schema; baseline of 3 is appropriate.

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 selects an option in a dropdown (<select>), which is a specific verb+resource and distinguishes it from siblings like 'click' or 'check'.

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., using 'click' for custom dropdowns or 'check' for checkboxes). The description lacks context for when-not-to-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?

Describes the waiting behavior adequately, but no mention of blocking nature or safety. With no annotations, description covers the essential trait.

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, front-loaded, no wasted words; perfectly 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?

For a simple one-parameter, no-output tool, the description provides complete context: what, why, and default value.

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 already fully describes the single parameter (ms) with default and meaning; description adds no extra value beyond 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 action (wait) and the purpose (for JS execution or page rendering), distinguishing it from sibling tools like wait_for_selector.

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?

Implied usage for waiting after browser actions, but lacks explicit when-not-to-use or alternatives.

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?

Describes read-only operation checking launch status and URL. No annotations provided, so description covers key behavioral traits adequately, though error handling unspecified.

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, no wasted words. Front-loaded with purpose.

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?

Covers main points but 'etc.' vague; could list all return fields or behavior when browser not launched. No output schema to compensate.

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?

No parameters; schema coverage 100%. Description adds no parameter info, but baseline is 4 for zero-parameter tools.

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 tool views browser current status (launch state, current URL). Distinct from sibling action tools (launch, navigate, close) that modify state.

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?

Implied usage: use to check browser state before actions. No explicit alternatives or when-not guidance, but purpose is self-evident given siblings.

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 description must fully disclose behavior. It only mentions 'appear' but ignores details like timeout handling, error on failure, or that state enum includes detached/hidden (waiting for disappearance). 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?

Single sentence, front-loaded, no wasted words. Could include more details without becoming verbose, but current length is acceptable.

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?

Tool has 3 parameters, all documented. Lacks details on return value, timeout behavior, and precise semantics of each state. Adequate but not thorough.

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 100% with meaningful descriptions for all parameters. The description adds no extra meaning beyond the schema, so baseline 3 is appropriate.

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 waits for a specified element to appear, with use-case examples (page loading, pop-ups). However, it does not explicitly differentiate from sibling tools like 'wait_for_url'.

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 scenarios ('可用于等待页面加载、弹窗等') but provides no explicit when-to-use or when-not-to-use guidance, nor alternatives.

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; the description mentions wildcard support but does not disclose whether the tool waits for navigation completion or throws errors if the URL does not change.

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 with no wasted words, effectively communicating the tool's purpose.

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 and lack of output schema, the description is adequate, though it could mention return behavior or error conditions.

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 covers 100% of parameters with descriptions; the description adds value by noting wildcard support, which enhances understanding beyond the 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's action (wait) and resource (URL), and distinguishes it from siblings like wait_for_selector by specifying it waits for page navigation to a URL.

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 waiting for a URL change but does not explicitly state when to use this vs alternatives like wait_for_selector or navigate.

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