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

With no annotations, the description carries the full burden. It does not disclose behavioral traits like handling of empty history stack or whether it triggers events. Adequate but lacks clarity on edge cases.

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, straightforward sentence efficiently conveys the tool's purpose with 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?

The description is minimal and covers basic purpose but lacks completeness regarding prerequisites (e.g., previous page existence) or return values. Acceptable for a simple action but could be more 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?

The tool has 0 parameters, and schema description coverage is 100%. The description adds no parameter info, which is acceptable as there are none to describe.

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

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

The description clearly states the verb 'navigate back' and the resource 'browser history', directly indicating the tool's function. It distinguishes from sibling tools like 'cloak_forward' and 'cloak_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 context through the name 'back' but does not provide explicit guidance on when to use this tool over alternatives, such as conditions for history availability.

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

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

No annotations are provided, and the description only states the action without disclosing behavioral traits such as waiting behavior, error handling, or prerequisites (e.g., element visibility).

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 tool's purpose with no redundancy.

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 click tool with one parameter and no output schema, the description is adequate but lacks context on what happens if the element is not found or not clickable.

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 an example format for the ref parameter, but it does not explain constraints or expected values 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 action ('Click') and the resource ('element identified by its ref ID') with an example format ('e.g. @e5'), distinguishing it from siblings by specifying the use of a ref from a snapshot.

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 cloak_hover or cloak_drag, nor any prerequisites or when-not-to-use scenarios.

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

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

No annotations are provided, placing the burden on the description. It mentions 'clean up resources' but does not specify what that entails (e.g., clearing local storage, closing connections). This is 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?

The description is very concise at one sentence, front-loading the primary action. Every word is necessary and there is no wasted 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?

For a simple terminal action with no parameters or output schema, the description is sufficiently complete. It tells the agent the core function, though it could mention that it should be used last in a sequence.

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 description coverage is 100%. The guideline states 0 parameters sets baseline to 4. The description adds no additional param info, but none is 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 clearly states 'Close the browser and clean up resources', providing a specific verb and resource. It distinguishes from siblings like cloak_navigate or cloak_click, which perform other browser actions.

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

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

The description implies usage when you want to terminate the browser session, but does not explicitly provide when-not-to-use or alternatives. While it is a terminal action, no guidance is given for edge cases 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?

No annotations are present, so the description bears full responsibility. It fails to disclose what happens when 'expression' is evaluated (e.g., return value, side effects), or the effect of 'clear' on subsequent outputs.

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, efficient sentence. It is front-loaded and lacks fluff, but could benefit from separating the two use cases for clarity.

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?

Without output schema or annotations, the description leaves gaps: no return format, error handling, or examples. Given the tool's complexity and sibling overlaps, it is insufficiently 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%; the description adds no extra meaning beyond the schema definitions. Baseline of 3 applies as it neither enriches nor detracts.

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 browser console output or evaluates JS expressions. However, it does not differentiate from sibling 'cloak_evaluate', which also evaluates expressions, creating potential confusion.

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 'cloak_evaluate' or other console-related tools. No context on prerequisites or exclusions provided.

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

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

No annotations are provided, so the description must carry the full burden. It only says 'drag an element', but does not describe what drag entails (e.g., mouse events, visibility requirements, potential page changes). This lacks necessary behavioral details.

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 immediately conveys the core purpose. No unnecessary words or structure.

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 (UI interaction) and lack of output schema, the description is too brief. It does not mention potential side effects, return values, or how the drag action is performed (e.g., simulation details).

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% and descriptions like 'Source element reference' are clear. The description does not add more 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 action ('drag') and the resource ('element from one position to another'). It is specific enough to distinguish from sibling tools like cloak_click or cloak_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 provides no guidance on when to use this tool versus alternatives such as scroll, click, or navigate. No context about prerequisites or exclusions is 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?

No annotations are provided, so the description must fully disclose behavioral traits. The description is too minimal: it does not mention that the expression runs in the browser context, may have side effects, or that it returns a value. This is insufficient for a powerful operation like eval.

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

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

The description is concise, using a single sentence to state the purpose. It front-loads the key action. However, it could be slightly expanded without being verbose, hence 4.

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 and potential risks of evaluating JavaScript, the description is severely incomplete. It lacks information on return value, security implications, asynchronous behavior, and error handling. With no output schema or annotations, this is inadequate.

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 parameter 'expression' is already documented in the schema. The description adds no additional 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 evaluates JavaScript expressions in the page context. It is a specific verb-resource pair that distinguishes from sibling tools (click, navigate, etc.), which are other 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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, contexts, or when not to use it. For a potentially dangerous eval tool, this is a significant gap.

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 full burden. It only states the basic action without disclosing behavioral traits like whether it waits for page load, includes relative/absolute URLs, or affects page 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?

Single sentence, front-loaded with the action and output format. No wasted words; highly concise.

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

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

Given no parameters, no output schema, and no annotations, the description is minimal but covers the basic purpose. However, it lacks details like output format specifics (absolute vs relative URLs) or assumptions about page 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?

With zero parameters, baseline is 4. The description adds no param details since none exist, but it clarifies the tool's purpose beyond the empty 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 (extract all links) and the output format (JSON). It distinguishes from sibling tools, as no other tool explicitly extracts links; siblings are navigation or interaction 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 implies usage for extracting links but offers no explicit when-to-use or when-not-to-use guidance, nor alternatives. The context is clear but lacking exclusions.

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

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

No annotations provided; description lacks any behavioral details beyond purpose. Does not mention that optional 'submit_ref' triggers click after fill, nor any side effects or state changes. Very minimal 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?

Extremely concise (one sentence) but at the expense of valuable details. Not wasteful, but under-specification reduces utility.

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, no annotations, and two parameters including an optional submit, the description is insufficient. Agent lacks info on return values, field validation, error behavior, or whether submit_ref is required for forms without native submit.

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% meaning the schema already documents both parameters adequately. Description adds no additional semantics beyond 'fill multiple form fields' – no clarification on ref/value interpretation or order of operations.

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 uses specific verb 'fill' and resource 'multiple form fields at once', clearly indicating bulk operation. Distinguishes from siblings like 'cloak_type' (single field) and 'cloak_click' (submit action). Could explicitly contrast with single-field tools.

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

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

No guidance on when to use this tool vs siblings like 'cloak_type' or 'cloak_click' for individual fills or sumbits. Agent must infer usage context from name alone.

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

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

With no annotations, the description carries full burden for behavioral disclosure. It fails to mention side effects, behavior when no forward history exists, or any prerequisites. The description is too sparse.

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 is appropriately short for a parameterless 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?

Given the simplicity of the tool (no params, no output schema), the description could be more complete. It lacks details about error handling or limitations, leaving the agent uninformed about edge 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?

There are no parameters, so the baseline is 4 per rubric. The description adds no parameter info, but none is needed since the schema covers all (zero) 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 action ('Navigate forward') and the resource ('browser history'). It distinguishes from siblings like 'cloak_back' which navigates backward, making the purpose 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?

No guidance is provided on when to use this tool versus alternatives (e.g., when there is no forward history). The description lacks explicit context for usage decisions.

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

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

No annotations provided, so description must fully cover behavioral traits. It does not mention that the tool is read-only, nor disclose any side effects, permissions, or rate limits. Only repeats the basic function already clear from name and schema.

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 key information. No wasted words. Perfectly concise for a simple 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 read tool with fully described parameters and no output schema, the description covers the core purpose. Minor omission: it doesn't mention what the return value looks like or behavior on missing selector, but these are inferable from parameter names.

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 having a description. The tool description adds no additional meaning beyond what the schema provides (e.g., selector, text_only, max_length). 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?

Description clearly states verb 'Get' and resource 'text or HTML content of an element or the entire page'. It distinguishes from sibling tools like cloak_get_images and cloak_screenshot by focusing on content retrieval.

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

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

No guidance on when to use this tool vs alternatives (e.g., cloak_evaluate, cloak_snapshot). No exclusions or context provided. Just states what it does 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 are present, so the description bears full burden. It correctly conveys a read-only operation, but does not explicitly state that it has no side effects, does not alter the page, or any other 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 a single, front-loaded sentence with no wasted words. Every part earns its place: what it does, scope, and output detail.

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 tool with no output schema, the description adequately explains functionality. It could specify return format or that it works on the currently loaded page, but that is implied by sibling context. Nearly 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?

The input schema has zero parameters, so schema coverage is 100%. The description adds no parameter info because none exist. Per guidelines, 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 clearly states the tool retrieves all images on the current page with URLs and alt text, using specific verb 'Get' and resource 'images'. It distinguishes well from sibling tools like cloak_screenshot or cloak_extract_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 when needing image info, but does not explicitly state when to use versus alternatives or provide exclusions. Sibling tool names hint at differentiation, but no direct guidance is 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?

No annotations are provided, so the description carries the full burden. It only states the action without disclosing behavioral traits such as whether it waits for the element to be visible, whether it triggers hover events, or if it has any side effects. For a tool that simulates user interaction, more transparency is needed. A score of 2 reflects the lack of essential behavioral details.

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, brief sentence with no extraneous words. It is well front-loaded and communicates the core action efficiently. Every word 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 covers the basic action. However, it does not explain what 'hover' means in terms of UI automation (e.g., 'simulates moving the mouse cursor over the element and triggering any associated hover effects'). Considering the number of sibling tools, a slightly richer description would improve completeness. Hence, a score of 3.

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 describes the 'ref' parameter as 'The element reference.' The description adds 'ref ID,' which is slightly more specific but does not provide substantial new meaning. With 100% schema coverage, the baseline is 3, and the description offers marginal improvement.

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 ('hover') and the target ('element identified by its ref ID'). It uses a specific verb and resource, which is good. However, it does not explicitly differentiate from similar tools like cloak_click or cloak_press, but the action 'hover' is distinct enough to convey the purpose. A score of 4 is appropriate because it is clear but lacks additional context that could make it excellent.

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

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

There is no guidance on when to use this tool versus alternatives. For example, it does not explain that hover is used to trigger hover effects or to position the mouse before clicking. Without such context, the agent has to infer usage from the name alone, which is insufficient for complex scenarios. Therefore, a score of 2 is warranted.

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, placing the burden on the description. It fails to mention that the tool is read-only or non-destructive, but the simple nature (0 parameters, informational) makes this omission minor.

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 unnecessary words, perfectly concise and front-loaded with the 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?

For a zero-parameter informational tool with a straightforward output, the description is fully complete. No additional context needed.

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 is empty (0 parameters) with 100% coverage; the description adds value by listing the returned data (URL, title, viewport), exceeding the schema's information.

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 retrieves browser session information (URL, title, viewport). It uses a specific verb ('Get') and resource ('current browser session'), distinguishing it from sibling tools that perform actions like navigation 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?

The context for use is clear: when needing session details. While it does not explicitly mention when not to use or alternatives, the sibling list implies this is the sole info- retrieval tool, so the guidance is adequate.

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 uses the adjective 'stealth' but does not elaborate on what behavioral traits that entails (e.g., anti-detection measures, session isolation). Without annotations, the description carries full burden, yet it omits critical details like whether this is a read-only or destructive operation, resource cleanup, or state persistence. It is minimally acceptable but lacks 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 extremely concise—just two short sentences—and front-loads the core action. Every word is necessary; no redundant or filler content. Excellent structure for quick comprehension.

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 is a launch operation with 0 required parameters, high schema coverage, and no output schema, the description is minimally complete. It does not explain return values, error conditions, or what happens upon multiple invocations. The low complexity reduces the need for more, but the lack of any return or side-effect description is a gap.

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 9 parameters are fully described in the input schema (100% coverage), so the schema already communicates their meaning. The description adds no additional semantic detail beyond what is in the schema, meeting the baseline expectation.

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 'stealth CloakBrowser instance' using specific verb 'launch' and resource 'stealth CloakBrowser instance'. It distinguishes from sibling tools by noting this must be called before any other cloak tool, making its role as the initial setup action 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?

Explicitly instructs 'Call this before any other cloak tool', providing precise when-to-use guidance. This precludes using other tools without first invoking this one, establishing a clear ordering constraint.

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

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

No annotations are provided, and the description does not disclose potential side effects (e.g., overwriting current state) or error handling, leaving gaps for a modifying 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, clear sentence with no unnecessary words—exemplary 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 tool's simplicity (one parameter, no output schema), the description is largely complete but could mention return values or potential errors for full clarity.

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% for the single parameter 'path', with a description in the schema. The tool description adds no further 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 specifies the action (load) and resource (browser storage state from a JSON file), clearly distinguishing it from its sibling tool 'cloak_save_storage_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?

No explicit guidance on when to use this tool vs alternatives; usage is implied but not stated.

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

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

With no annotations, the description must fully disclose behavior. It mentions 'return a compact snapshot' but does not define 'compact snapshot', nor does it address loading states, error handling, redirects, or side effects like changing the current page context.

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

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

The description is a single, efficient sentence with no unnecessary words. It is front-loaded with the action and resource, though it could benefit from slight expansion on behavior.

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

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

Given the tool's simplicity (one parameter, no output schema), the description is minimally adequate. It states the core function but lacks details on output format, timing, and side effects that would fully inform an 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?

The schema already provides 100% coverage for the single 'url' parameter. The description adds 'URL' which duplicates the schema. It does not add additional meaning beyond what the schema states.

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

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

The description uses a specific verb 'navigate' and resource 'URL', and clearly indicates it returns a compact snapshot. This distinguishes it from siblings like cloak_back and cloak_forward which are navigation history 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 implies usage for loading a new page, but does not explicitly state when to use this tool versus alternatives like cloak_get_content or cloak_snapshot. No exclusions or conditional logic are provided.

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

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

The description only says 'Press a keyboard key' without detailing how the keypress is simulated, whether it's a press-and-release, if it requires focus on an element, or any side effects. With no annotations, more transparency is needed.

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 is front-loaded with the action. However, it could be slightly expanded to improve completeness without losing 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?

For a simple tool with one parameter and no output schema, the description adequately covers the core function. However, it lacks details about behavioral semantics like event dispatching, which could be important for an AI agent.

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

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

The schema describes 'key' as 'Key to press.' The description adds value by listing common key examples (Enter, Tab, Escape, ArrowDown), helping the agent understand valid inputs beyond the schema's generic description.

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

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

The description clearly states the tool presses a keyboard key and provides examples like Enter, Tab, Escape, ArrowDown, etc. It distinguishes from sibling tools such as cloak_click (mouse click) and cloak_type (typing text).

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

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

No explicit usage guidance is given. The context of sibling tools implies it should be used for single key presses rather than typing sequences or mouse actions, but there is no direct statement on when to use or not use this 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?

No annotations are provided, so the description carries full transparency burden. It discloses that state is saved to a JSON file but omits critical behaviors: whether it overwrites existing files, error handling for invalid paths, or if it includes all storage (cookies, localStorage) comprehensively. The agent cannot infer side effects or safety guarantees.

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 efficiently conveys the core functionality. No extraneous words or redundant information. It is properly front-loaded with the action and resource.

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 absence of an output schema and annotations, the description should provide more context. It does not mention return values (e.g., success confirmation) or error scenarios. The sibling tools include a load counterpart, but no linking is provided. For a storage-related tool, completeness is lacking.

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

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

The schema has 100% coverage with a single parameter 'path' described as 'File path to save.' The description adds minimal extra meaning by specifying 'JSON file', reinforcing the expected format. However, this is a minor addition; the schema already conveys the essential information, so a 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: saving browser storage state (cookies, localStorage) to a JSON file. It uses a specific verb ('Save') and resource ('browser storage state'), and the mention of 'JSON file' provides output format. Among siblings, 'cloak_load_storage_state' is a clear counterpart, aiding 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?

The description provides no guidance on when to use this tool versus alternatives (e.g., when to save state vs. other storage operations). It does not mention prerequisites, postconditions, or complementary tools like 'cloak_load_storage_state'. The agent receives no contextual 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?

Without annotations, the description must disclose behavioral traits. It only states the basic function and output format, omitting crucial details like whether the screenshot captures the full page or viewport, any side effects, or prerequisites. The optional parameters 'question' and 'annotate' are not explained in terms of their impact on 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 extremely concise with two short sentences, no redundancy, and front-loaded information. Every word earns its place, efficiently conveying the primary action and output.

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 with two optional parameters and no output schema, the description is inadequate. It fails to explain the purpose of the 'question' parameter or how 'annotate' alters the screenshot. The return value is stated as PNG, but details about image dimensions or behavior under different page states are missing, leaving significant 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 description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the schema. While the schema sufficiently describes the parameters, the description does not clarify how 'question' interacts with the screenshot or why 'annotate' might be used, missing an opportunity to enhance understanding.

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 ('take a screenshot') and the resource ('current page'), and specifies the output format (PNG). However, it does not differentiate from siblings like 'cloak_snapshot', which might also capture visual state, lacking specificity about the exact nature of this screenshot tool.

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. There is no mention of which scenario is appropriate for screenshotting vs. using other tools like cloak_snapshot or cloak_get_content, leaving the agent without decision-making context.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. It only states 'Scroll the page in a direction' without detailing whether scrolling is smooth, how much it scrolls, or what happens at page boundaries.

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 that is clear and to the point. 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 (one parameter, no output schema), the description is minimally adequate but lacks behavioral context that could affect agent decisions, such as scroll amount or animation behavior.

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 one enum parameter. The description adds no new meaning beyond the schema: it simply mirrors the schema's 'Direction to scroll.' 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?

Description clearly states the tool scrolls the page in a direction. The name 'cloak_scroll' along with the description effectively communicates its purpose, though it doesn't explicitly differentiate from sibling tools like cloak_back or cloak_forward.

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

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

No guidance on when to use this tool over alternatives such as cloak_back, cloak_forward, or cloak_click. 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?

No annotations are present, so the description carries the full burden. It does not disclose whether the tool clears previous selections, handles multi-select, or triggers events. This is insufficient for a select option 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 extremely concise at 7 words with no fluff. However, it lacks important details, making it borderline under-specified. For conciseness alone, it earns a 4.

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 2 required parameters and no output schema, the description should clarify how values match options (e.g., by value attribute, label, or index), and whether multiple selection is supported. The lack of this context makes it incomplete.

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

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

Schema coverage is 100% for both parameters, but the descriptions are minimal and add no additional meaning beyond the names. Baseline for high coverage is 3, and the description does not improve upon it.

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

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

The description clearly states the tool selects options in a <select> element, which is specific to HTML select elements. However, it does not differentiate from sibling tools like cloak_fill_form that might also affect selects, but the name and description are sufficiently clear.

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 guidelines are provided on when to use this tool versus alternatives like cloak_click or cloak_fill_form. The description lacks context on appropriate usage scenarios 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?

No annotations are provided, so the description carries full burden. It states the output type (text-based snapshot of accessibility tree) but does not disclose whether the operation is read-only, side-effect-free, or any limitations (e.g., performance, size constraints).

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 conveys the tool's purpose without extraneous words. 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?

Given the tool's complexity (1 parameter, no output schema, no annotations), the description is minimal. It omits details like the format of the output, how interactive elements are identified, and when to prefer this over sibling tools like cloak_get_content or cloak_screenshot.

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 one optional boolean parameter 'full' described as 'If true, return complete page content.' The description adds the context of 'accessibility tree with ref IDs' but does not elaborate on what 'complete page content' means relative to the default snapshot. 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 retrieves a text-based snapshot of the accessibility tree with ref IDs for interactive elements. This is specific and distinct from sibling tools like cloak_get_content or cloak_info, though it doesn't explicitly differentiate them.

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., cloak_get_content, cloak_screenshot). It does not mention prerequisites, context, or scenarios where this is preferred.

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 carries full burden. It describes the basic action but does not disclose behavior for edge cases like invalid ref IDs, whether it clears existing text, or other keyboard interactions. It is minimally adequate.

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

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

The description is a single, front-loaded sentence with no wasted words, effectively communicating 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 good schema coverage, the description is sufficiently complete. However, it could benefit from contextual hints about when to use type vs other input-related siblings.

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 baseline is 3. The description adds little beyond what schema already provides for each parameter; e.g., it does not clarify the relationship between 'text' and 'submit'.

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 'Type' and the resource 'input field identified by its ref ID', which is specific and distinguishes it from siblings like cloak_click or cloak_press.

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 siblings like cloak_fill_form or cloak_press. The description lacks context for appropriate usage scenarios.

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

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

With no annotations, the description carries the full burden. It only states the intent to wait but does not disclose what happens on timeout, whether it blocks, what it returns, or how conflicts (both selector and text provided) are resolved. The timeout parameter is documented in the schema, but behavioral details are missing.

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

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

The description is a single sentence of 10 words, front-loading the core purpose. Every word earns its place; there is no redundancy or filler. It achieves maximum conciseness while conveying the essential 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?

The tool is relatively simple with low complexity, and the schema covers all parameters. However, the description does not provide complete context: it omits details about return behavior, error handling, or the logical operator between selector and text. Given the lack of output schema and annotations, more context would be helpful for an agent to use this tool reliably.

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 baseline is 3. The description does not add any meaning beyond the schema; it merely paraphrases the parameter concepts. No extra context or usage hints for the parameters are given.

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 resource ('element or text to appear'), distinguishing it from other tools in the sibling list that perform different actions like clicking or navigating. However, it could be more precise by specifying that it waits for visibility or presence, and by clarifying the relationship between selector and text.

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

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

No guidelines are provided about when to use this tool versus alternatives. There is no mention of prior conditions (e.g., page already loaded), nor any comparison to similar tools like cloak_click or cloak_navigate. The agent receives no context on appropriate use cases.

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