Cloudflare Playwright MCP

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

The description simply restates the tool's action without adding behavioral context beyond what annotations already provide (destructiveHint=true, openWorldHint=true). It does not disclose potential side effects like navigation, form submission, or state changes.

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, which is concise. However, it is too brief and lacks sufficient detail to fully guide an agent, missing opportunities to add value 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 the tool's complexity (5 parameters, multiple siblings, no output schema), the description is severely incomplete. It omits return values, side effects, and usage context, leaving the agent underinformed for safe and 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 input schema already provides 100% description coverage for all 5 parameters. The description adds no additional meaning beyond the schema, so the 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 'Perform click on a web page', which is a specific verb and resource. It distinguishes from sibling tools like browser_hover or browser_drag, though it does not mention parameter-driven variations 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 is provided on when to use this tool versus alternatives like browser_press_key or browser_hover. There is no mention of prerequisites, when not to use it, or how to choose between click and other interaction 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?

Annotations already indicate destructiveHint=true and openWorldHint=true, so the description's simple statement is sufficient. It does not add extra context about side effects (e.g., unsaved data loss), but it does not contradict annotations.

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 that directly states the action. It is front-loaded 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?

Given no parameters, no output schema, and annotations covering destructive and open-world behavior, the description is adequately complete. The openWorldHint could be elaborated, but annotations already handle it.

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. With zero parameters, the description does not need to add parameter details; a baseline 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 'Close the page' clearly states the verb (close) and the resource (page), distinguishing it from sibling tools like browser_navigate or browser_tabs. It is specific and 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 provides no guidance on when to use this tool versus alternatives, such as browser_tabs for switching tabs or browser_navigate for leaving the page. There are no prerequisites or exclusions 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?

Annotations already provide readOnlyHint and destructiveHint, so the description adds no behavioral context beyond stating the return type. Does not disclose filtering behavior or session scoping.

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 concise but too vague; it lacks essential details such as the meaning of 'all' and the relationship to the level parameter. Not front-loaded with key 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?

Despite moderate complexity and no output schema, the description does not tie together the parameters or explain the output format. Leaves ambiguity about what 'console messages' entails.

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 the schema already documents parameters. The description does not add extra meaning beyond what the schema provides.

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 console messages, a specific verb-resource pair. It distinguishes itself from sibling tools like browser_click or browser_navigate, though the word 'all' could be slightly misleading given filtering options.

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 browser_network_requests. No exclusions or context for optimal 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?

Annotations already indicate destructiveHint=true and openWorldHint=true. The description adds minimal behavioral context beyond the action itself; does not explain interaction permissions, success/failure states, or whether it simulates real mouse events. With annotations present, this is adequate but not enriched.

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 is front-loaded and efficient. While more detail could be added, the information is present without unnecessary verbosity.

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?

No output schema, but the tool is a simple action. Without describing return behavior or failure modes, the description is minimally complete for its complexity. Could be improved by noting that the browser must have page 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?

The input schema has 100% description coverage, providing clear descriptions for each parameter. The tool description adds no additional value beyond what the schema already offers, meeting the baseline for this dimension.

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 'Perform drag and drop between two elements' uses a specific verb ('drag and drop') and resource ('elements'), clearly distinguishing it from sibling tools like browser_click, browser_drop, and browser_hover.

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 mention of prerequisites such as needing a page snapshot to obtain element references, or when not to use drag and drop.

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 provide readOnlyHint=false, destructiveHint=true, and openWorldHint=true. The description aligns by stating 'Drop files or MIME-typed data onto an element, as if dragged from outside the page,' implying page modification. It adds behavioral context (simulating external drag) beyond the annotations, which is helpful.

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: first defines the purpose, second provides a critical parameter guideline. No unnecessary words, front-loaded, and every sentence adds value. It is efficiently 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 tool's complexity (4 params, nested objects, no output schema), the description covers purpose and a key constraint. However, it does not mention what happens after the drop (e.g., event triggering) or elaborate on 'MIME-typed data' beyond schema. Still, it is adequately complete for the action.

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 descriptions for all parameters. The description adds value by explicitly stating the constraint 'At least one of 'paths' or 'data' must be provided,' which is not enforced by schema (only target is required). This clarifies a key usage rule 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 (drop), the resource (element), and the type of data (files or MIME-typed data). It distinguishes itself from siblings like browser_drag (internal drag) and browser_file_upload (different mechanism) by specifying 'as if dragged from outside the 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?

The description provides one usage guideline: 'At least one of 'paths' or 'data' must be provided.' However, it does not explicitly state when to use this tool versus alternatives (e.g., when to simulate an external drop vs. a click or file upload). No exclusions or context for selecting among siblings are given.

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 already indicate destructiveHint=true and openWorldHint=true, but the description adds no behavioral context, such as potential side effects, permission requirements, or interaction with page state. It does not contradict annotations, but it misses an opportunity to elaborate on risks.

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 that is front-loaded with the verb 'Evaluate'. It wastes no words, but is perhaps too brief for a tool with potential for complex usage.

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 the complexity of evaluating JavaScript, the description lacks details on return values, error handling, execution context, or limitations. With no output schema and only basic annotations, the description is insufficient for complete understanding.

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 100% parameter description coverage, so the baseline is 3. The tool description does not add any semantic information beyond what the schema already provides, which is sufficient but not enhanced.

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 evaluates JavaScript on a page or element, using a specific verb and resource. However, it does not differentiate from the sibling tool 'browser_run_code', which likely performs a similar function.

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 'browser_run_code'. There is no mention of prerequisites, context, or exclusions, 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?

The description only says 'Upload one or multiple files' and does not add behavioral details beyond what annotations provide (destructiveHint=true, openWorldHint=true). It misses explaining interactions like opening a file dialog or needing a file input.

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 sentence, no redundancy. While minimal, it is efficient and front-loaded. Slightly better than a tautology but still sparse.

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 one parameter and annotations, the description is minimally acceptable. However, it lacks guidance on destructive behavior (destructiveHint=true) and prerequisites, leaving gaps.

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%: the 'paths' parameter already has a clear description. The tool description adds no additional meaning beyond the schema, meeting baseline expectations.

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 uploads files, aligning with the tool name. It is specific enough to distinguish from sibling browser tools, though it does not explicitly mention browser 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 over alternatives or what prerequisites exist (e.g., needing a file input element). The description omits 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?

The description adds no behavioral context beyond the annotations. Annotations indicate destructiveHint=true but the description does not explain the nature of modifications (e.g., page state changes, potential events triggered). The description is too brief to disclose any behavioral traits.

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 (3 words) but fails to provide critical information. Conciseness is not valuable here as it omits necessary context. The description is under-specified rather than efficiently written.

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 the input schema (array of objects with multiple required fields) and no output schema, the description is completely inadequate. It does not explain how fields are processed, ordering, error behavior, or interaction with page state, leaving the agent without sufficient 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?

Schema description coverage is 100% with each field having a description. The tool description adds no additional meaning beyond the schema. Baseline score of 3 is appropriate as the schema already documents parameters adequately.

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 'Fill multiple form fields' is a vague statement of purpose. It indicates the tool fills form fields but does not specify what 'fill' entails (e.g., setting values, toggling checkboxes). It somewhat distinguishes from siblings like browser_type (single field) by mentioning 'multiple', but lacks explicit differentiation.

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 browser_type or browser_select_option. There is no mention of context, prerequisites, 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?

Annotations indicate destructiveHint=true and openWorldHint=true, but the description adds no behavioral context (e.g., what happens to the page, whether navigation occurs). The agent must guess the 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 very short, but it sacrifices informativeness for brevity. It could include a brief example or clarification without being 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 the simple parameter set and no output schema, the description is insufficient. It does not explain return behavior, error cases, or what constitutes a successful dialog handling.

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 the schema already documents both parameters. The description adds no additional meaning, 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 'Handle a dialog' is vague and does not specify what action is performed (e.g., accept, dismiss) or the type of dialog. It barely improves over the tool name.

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 sibling tools like browser_click or browser_fill_form. The context of dialogs is implied but not explained.

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 indicate destructiveHint true and readOnlyHint false, but the description does not elaborate on potential side effects (e.g., triggering hover states, popups). The description adds no additional behavioral context beyond the minimal annotation.

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, direct sentence with no unnecessary words. It efficiently communicates the basic action, though it could be slightly expanded 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 simplicity of the tool and lack of output schema, the description is minimally adequate but does not cover important details like event triggering, usage in sequences, or error cases.

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 descriptions for both parameters, so the description does not need to add much. However, it does not clarify how 'element' differs from 'target' or provide examples, leaving room for ambiguity.

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 ('hover') and the resource ('element on page'), effectively distinguishing it from sibling tools like click or drag. However, it could be more specific about the type of element or 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 is provided on when to use hover vs other interaction tools (e.g., click, drag), nor any conditions or prerequisites. The agent has no hints about scenario suitability.

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 already indicate destructiveness and open-world interaction, but the description adds no specifics about page load waiting, state changes, or fallback 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?

Single sentence with no wasted words, perfectly efficient for a simple navigation 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?

Lacks details on whether navigation waits for page load, handles redirects, or returns the final URL; basic but adequate for a straightforward tool with no 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 coverage is 100% with parameter description 'The URL to navigate to'. The tool description adds no additional meaning 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 'Navigate to a URL' clearly states the action (navigate) and resource (URL), distinguishing it from sibling actions like clicking or closing.

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., for back navigation use browser_navigate_back), nor any 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?

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description does not need to add much. It adds no extra behavioral context beyond the obvious 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?

A single, concise sentence with no unnecessary words. Every part is essential.

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 parameterless action with no output schema, the description is largely complete. It could mention edge cases like empty history, but overall it adequately defines 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?

No parameters exist, and schema coverage is 100%. According to rubric, 0 params earns baseline 4. Description adds no parameter info, which 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?

Description clearly states the action 'Go back to the previous page in the history'. It uses a specific verb and resource, and distinguishes from sibling tool browser_navigate which goes to a specific 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?

No guidance on when to use this tool versus alternatives or when it might fail (e.g., no history). The description is functional but lacks context for appropriate 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds 'since loading the page' but does not elaborate on behavior like data volume or performance impact. It is consistent with annotations.

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 that directly states the tool's purpose. No extraneous information, front-loaded with the core 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?

While the description is clear, it lacks details about the return format (e.g., list of objects with URL, method). With no output schema, the agent may need more context. However, annotations and schema parameters provide some support.

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 all parameters are described in the schema (e.g., static, filter). The description adds no additional 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 it returns network requests since page load. The verb 'Returns' and resource 'network requests' are specific, and it distinguishes from sibling tools like browser_console_messages.

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 vs alternatives like browser_navigate or browser_console_messages. It is implied that this tool is for network request inspection, but no when-not or prerequisites 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?

Annotations note destructiveHint and openWorldHint, but the description adds no behavioral context beyond 'press a key'. It does not mention that key presses can trigger page events, affect focus, or what happens with invalid key values.

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 sentence, no wasted words. The description is appropriately sized for a simple tool with one parameter.

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 one param and no output schema, the description is minimally adequate. However, it lacks mention of the context (e.g., presses on focused element, vs browser_type) which slightly reduces 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?

The input schema covers the single 'key' parameter with helpful examples (e.g., ArrowLeft, a). Since schema coverage is 100%, the description adds no additional parameter info. 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 action ('press') and resource ('key'), but it does not differentiate from sibling tools like 'browser_type' which types a sequence. Adding 'single key' would improve distinction.

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., 'browser_type' for multiple characters, 'browser_fill_form' for forms). No exclusions 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?

Annotations indicate destructiveHint true and readOnlyHint false, but the description adds no explanation of what 'destructive' means (e.g., viewport change affects page layout) or any other behavioral context beyond the bare verb.

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 the 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?

For a simple tool with two numeric params and no output schema, the description is nearly complete. Could optionally mention units (pixels) 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?

Schema coverage is 100%; both width and height are described with types and required. The description adds no additional meaning beyond what the schema provides.

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 'Resize the browser window' clearly states the action and resource, and it distinguishes this tool from siblings like navigating or clicking.

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, and no mention of 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?

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description's minimalism is acceptable. However, it adds no extra behavioral context (e.g., potential page state changes, side effects) beyond what annotations provide.

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, readable sentence. It is concise but not underspecified—it effectively communicates the core function without 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?

The description does not explain return values, error handling, or that the tool can load code from a file. Given the lack of an output schema and the tool's power (destructive, open world), more context is needed for complete understanding.

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 100% coverage with detailed descriptions for both parameters (code and filename). The description adds no additional meaning, so the 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 'Run Playwright code snippet' clearly states the action and resource. It distinguishes this tool from siblings like browser_click or browser_navigate because it executes arbitrary Playwright code, not a specific browser 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?

The description provides no guidance on when to use this tool vs. alternatives like browser_evaluate or other specific actions. There is no mention of prerequisites, when to avoid it, or when it is preferable.

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 already indicate destructiveHint=true (modifies UI state) and openWorldHint=true (potential side effects). The description does not add any behavioral context beyond this, such as whether it triggers events or requires permissions. It meets the baseline but adds no extra 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 with no filler. It is appropriately sized and front-loaded with the core 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?

For a simple tool with full schema coverage and no output schema, the description is sufficient. It could mention multi-select capability (implied by 'values' array) but that is already in the schema. It lacks context like dropdowns with search or custom options, but given the sibling set, this is 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 the description adds no parameter details beyond what the schema provides (e.g., element for permission, target as selector, values as array). The description does not compensate for missing schema descriptions, but they are already present.

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 'Select an option in a dropdown', using a specific verb and resource. It distinguishes this tool from siblings like browser_click and browser_fill_form, as it is focused exclusively on dropdown selections.

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 (e.g., browser_click for regular clicks) or prerequisites (e.g., the dropdown must be visible). Usage context is only implied by the tool name.

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 already set readOnlyHint=true and destructiveHint=false; the description adds that the snapshot is an 'accessibility snapshot', hinting at its nature, but does not detail behavioral traits like what elements are included or performance implications.

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, concise and to the point, though the phrasing 'this is better than screenshot' is slightly informal. No 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 presence of annotations and full schema coverage, the description is adequate but lacks details about the output format or return value, which is not provided by an 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?

Input schema covers all 4 parameters with descriptions (100% coverage); the description adds no additional meaning beyond the schema, so 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 the tool captures an accessibility snapshot of the current page and explicitly distinguishes it from screenshots by claiming superiority, which helps the agent differentiate it from sibling tool browser_take_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 implies use when an accessibility snapshot is better than a screenshot, but lacks explicit when-to-use or when-not-to-use guidance, nor mentions alternatives beyond the brief comparison.

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 already indicate destructiveHint=true and readOnlyHint=false. The description aligns with these but adds no extra context (e.g., effect on browser state, whether closing is reversible). No contradictions.

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, immediately front-loaded with the four actions. Every word earns its place. No unnecessary elaboration.

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, 4 actions, and no output schema, the description is minimal. It does not explain return values or behavior after selecting a tab. Could be expanded to disambiguate from sibling tools like browser_close.

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 clear parameter descriptions. The description does not add meaning beyond the schema; it merely restates the action enum labels. 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 can list, create, close, or select a browser tab, using specific verbs and a clear resource. However, it does not differentiate from sibling tools like browser_close (which closes the whole browser) or browser_navigate, which could confuse agents.

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 vs alternatives. The description lists actions but does not explain when to choose 'list' over 'select', or when to use browser_tabs 'close' instead of the separate browser_close tool.

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 already declare readOnlyHint=true and destructiveHint=false, so the description is consistent and adds the behavioral constraint that the screenshot cannot be used for interactive actions. This adds value beyond annotations, but doesn't elaborate on other traits like permission requirements 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 two sentences long with no superfluous information. It is front-loaded with the primary purpose and immediately provides usage guidance, making it efficient and easy to parse.

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

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

For a tool with 5 parameters (all fully described in schema) and no output schema, the description adequately covers purpose, usage, and differentiation. No additional explanation of return values is needed, as the tool is a simple capture.

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 parameters are well-documented in the schema. The description does not add additional meaning beyond what the schema provides, thus meeting the baseline for full coverage.

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 ('Take a screenshot of the current page') and differentiates it from a sibling tool (browser_snapshot) by noting that the screenshot cannot be used for actions. This provides specific verb and resource scope, distinguishing it from alternatives.

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 explicitly tells when to use the tool (taking a screenshot) and when not to (for performing actions, use browser_snapshot instead). This provides clear context and alternatives, meeting the highest standard.

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 declare destructiveHint=true and openWorldHint=true, and the description does not contradict them. However, it adds no behavioral context beyond the annotations, such as confirmation prompts or character 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?

A single sentence that is front-loaded with the verb, conveying the core functionality without 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 the simplicity of the tool and the rich parameter descriptions in the schema, the description is nearly complete. It could mention that typing overwrites existing content or that the element must be focused, but overall 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?

All 5 parameters have schema descriptions, so the description adds no extra meaning. 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 the action ('type text') and the resource ('editable element'), distinguishing it from sibling tools like browser_click or browser_press_key.

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 mention of when not to use or prerequisites like element visibility or focus.

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 already indicate read-only behavior (readOnlyHint=true, destructiveHint=false). The description adds minimal context (waiting for conditions) but does not specify polling behavior or timeout details. No contradiction with annotations.

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 is clear and efficient, with no redundancy or 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 read-only tool with three optional parameters and no output schema, the description covers the main use cases. However, it could clarify mutual exclusivity or default behavior, but overall it is 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?

Input schema has 100% description coverage for all three parameters. The description mentions text appearance/disappearance and time, matching the parameters, but adds no additional meaning beyond what the schema already provides.

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 (text appearance/disappearance or a time duration). It is specific and distinguishes from sibling tools like browser_click or browser_navigate.

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 contexts (waiting for text or time) but does not explicitly state when to use this tool versus alternatives like browser_click or browser_fill_form. No exclusions or comparisons are provided.

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