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

No annotations are provided, so the description must fully convey behavior. It mentions returning updated page context but omits details about side effects, failure modes, or element matching behavior when multiple elements match.

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 action, no extraneous text. Every sentence serves a 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 full schema descriptions, the description adequately covers the purpose and return value. It does not need to explain output since no output schema exists.

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 each parameter described. The description reinforces the identification methods (CSS, XPath, text) but adds no new information 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 action ('Click an element') and the resource ('on the current page'), and distinguishes itself from siblings by specifying the core interaction type.

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 the tool (to click elements) but does not provide explicit exclusions or comparisons with siblings like browser_type or browser_scroll.

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 explicitly states the tool executes JavaScript and returns the result, and lists blocked functions. It does not mention error handling or return type details, but the restrictions clarify safety.

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 purpose, followed by restrictions. Every sentence adds essential information with no redundancy or fluff.

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 covers the basic purpose and constraints but lacks details on return value format, error behavior, or potential side effects. Given no output schema, some additional context would be helpful.

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%, providing a baseline of 3. The description adds value by explaining the execution context and restrictions beyond the schema's parameter description, which only says 'JavaScript expression to evaluate'.

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 'execute' and the resource 'JavaScript in the current page context' with the outcome 'return the result'. It distinguishes from sibling tools like browser_click by emphasizing execution of code rather than UI interactions.

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 clear context on when to use (safe DOM read operations) and restrictions (blocked functions like eval, fetch). However, it does not explicitly suggest alternative tools for non-read operations, though the restrictions implicitly guide 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?

Without annotations, the description reveals that by default no image tokens are consumed, the screenshot is discarded after OCR, and visual mode returns a PNG. This provides useful behavioral insight, though it omits potential side effects like cookie handling or timeout 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 two sentences, no wasted words. The first sentence states the core purpose, the second explains key options and defaults. It is front-loaded and 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?

The description explains the return value sufficiently for an agent to understand what to expect (DOM + OCR text, optionally PNG). Given no output schema, this is adequate. However, it does not cover error conditions or timeouts, which could be helpful.

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 description adds meaningful context beyond the schema: it explains the default (text-only, zero image tokens), the effect of visual=true, and that headless mode defaults to true. This helps the agent select parameters correctly.

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 'Open a URL' and the resource 'browser', and specifies the return value as 'page context (DOM elements + OCR text)'. This distinguishes it from siblings like browser_click or browser_screenshot.

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 explains the default text-only mode and how to enable visual output, but does not explicitly state when to use this tool instead of alternatives like browser_read or browser_screenshot. The context is clear but lacks explicit when-not-to-use guidance.

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 carries full burden. It states it's read-only (no navigation/clicking) and returns DOM+OCR, but lacks details on side effects, performance, or limits. Adequate but not comprehensive.

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 sentence that covers purpose and constraints without any wasted words. Highly 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?

Given one simple parameter and no output schema, the description is nearly complete. It could mention the optional return of base64 PNG, but overall it sufficiently informs 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 100% with a single boolean parameter (visual). The description adds no extra meaning beyond what the schema already provides, 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 reads the current page context (DOM elements + OCR text) and explicitly distinguishes it from navigation or clicking, making its purpose 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?

The description implies use for read-only context capture, contrasting with interactive tools. It could be more explicit about when to use this over browser_screenshot, but the distinction is clear.

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, but description clearly discloses that the screenshot is discarded unless visual=true, and that it returns an OCR-based text map. Covers key behavior, though could mention that a page must be loaded.

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, no filler, immediate purpose and parameter explanation. Efficient and 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?

For a simple tool (1 optional param, no output schema), the description covers purpose, parameter, and a nuance (screenshot discarding). Lacks explicit mention of prerequisite (page must be navigated).

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?

Only one boolean parameter (visual) with 100% schema coverage. Description mentions the parameter's effect (base64 PNG) and default, adding minimal value beyond the schema's own 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?

Description states 'Capture the current page and return an OCR-based text map' – specific verb and resource, and distinguishes from sibling tools like browser_read (DOM reading) and browser_scroll (scrolling).

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 extracting text from rendered page (e.g., images), but no explicit guidance on when to use versus alternatives like browser_read or browser_evaluate for script-controlled content.

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 disclose behaviors. It mentions scrolling and the visual parameter, but does not clarify if scrolling is smooth, if it handles dynamic content, or what happens when both selector and direction are specified. Lacks full behavioral 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?

Two concise sentences that front-load the purpose and quickly cover the two usage modes. No redundant or unnecessary 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 tool's simplicity, the description covers the main usage scenarios. However, it could mention what happens with conflicting inputs (e.g., both direction and selector) or edge cases. Without output schema or annotations, a bit more detail on return behavior would improve 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 covers all four parameters with descriptions. The description repeats the parameter usage but adds no new meaning beyond stating the default pixel value (800) and that visual returns base64 PNG. With 100% schema coverage, the description adds minimal additional 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?

Description clearly states the tool scrolls the current page and specifies two modes: direction with optional pixel amount, or a selector to scroll element into view. This distinguishes it from sibling tools like browser_navigate or browser_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?

Explains when to use each scrolling mode (direction/amount vs. selector), but does not explicitly warn against using this tool when alternatives like browser_navigate or browser_read are more appropriate. The sibling list provides context but the description itself lacks direct guidance.

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 disclosure. It notes that the tool types text, clears by default, and returns updated page context. This is adequate but does not cover potential error conditions, waiting behavior, or what happens if the element is not found. More detail would improve 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—two sentences that immediately convey the purpose and key behavior. Every sentence earns its place, and there is no unnecessary information. It is well-structured with the primary action stated first.

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 (four parameters, no output schema), the description covers essential aspects: what the tool does, default clearing, and return type. It could mention prerequisites like page load or element existence, but overall it provides sufficient context for an AI 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?

Schema description coverage is 100%, so the baseline is 3. The description adds minimal additional meaning beyond the schema, only clarifying that the clear parameter defaults to true. It does not elaborate on the 'text', 'selector', or 'visual' parameters, so it provides only marginal added 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 tool's function: typing text into an input field on the current page. The specific verb 'Type' and resource 'input field' make the purpose unambiguous. It also distinguishes from sibling tools like browser_click and browser_read, which have different 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?

The description mentions a key default behavior (clearing the field first), which is helpful. However, it does not explicitly state when to use this tool over alternatives or provide exclusions. The context implied by sibling names offers some guidance, but the description itself lacks explicit usage direction.

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