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

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the action and outcome but lacks details like whether this requires device permissions, if it's reversible, or potential side effects. For a zero-parameter tool, this is adequate but not comprehensive.

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

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

The description is a single, efficient sentence that front-loads the key action and result without any wasted words. It is appropriately sized for a simple tool with no parameters, making every word count.

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 (0 parameters, no annotations, but with an output schema), the description is complete enough for basic understanding. However, it could benefit from additional context like device-specific considerations or error cases, though the output schema may cover return values.

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 with 100% schema description coverage, so the schema fully documents the lack of inputs. The description does not need to add parameter information, and it appropriately focuses on the tool's action without redundancy, earning a baseline score of 4 for zero-parameter tools.

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

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

The description clearly states the specific action ('Press the home button') and the outcome ('return to the home screen'), which distinguishes it from sibling tools like 'open_app' or 'tap_back'. It uses a precise verb+resource combination that leaves no ambiguity about its 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?

The description implies usage context by specifying the result ('return to the home screen'), which helps differentiate it from alternatives like 'open_app_switcher' or 'open_control_center'. However, it does not explicitly state when not to use it or name specific alternatives, keeping it at a 4 rather than a 5.

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

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the two-step process (press home, then tap the app), the supported apps list, and the home screen context. This adds valuable context beyond what the minimal input schema provides, though it could mention error handling or performance aspects.

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

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

The description is appropriately sized and front-loaded: the first sentence states the core purpose, followed by implementation details and a list. Every sentence earns its place by providing essential information without redundancy, making it efficient and well-structured.

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

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

Given the tool's low complexity (1 parameter, no annotations, but has an output schema), the description is mostly complete. It covers purpose, usage steps, and supported apps. Since an output schema exists, it need not explain return values, but it could benefit from mentioning error cases or app-not-found behavior for full 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 has 0% description coverage, so the description must compensate. It adds meaning by specifying that the 'name' parameter refers to an app name from the supported list, which clarifies semantics beyond the schema's generic string type. However, it does not detail format constraints (e.g., case sensitivity), leaving some 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 specific action ('Open an app from the home screen by name') and distinguishes it from siblings like 'go_home', 'open_app_switcher', or 'tap' by specifying it's for launching apps from the home screen. It provides a concrete list of supported apps, making the purpose unambiguous.

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

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

The description explicitly states when to use this tool ('Open an app from the home screen by name') and includes a prerequisite action ('First presses home to ensure we're on the home screen'), which provides clear context. However, it does not specify when not to use it or mention alternatives like using 'tap' directly on an app icon, leaving some gaps in guidance.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the physical gesture required ('slow swipe up from bottom'), which is useful context beyond basic functionality. However, it doesn't cover potential side effects, success indicators, or error conditions, leaving gaps in behavioral understanding.

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

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

The description is a single, clear sentence that directly states the action and outcome with zero waste. It's front-loaded and appropriately sized for a simple, parameterless tool, making it highly efficient.

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

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

Given the tool's simplicity (0 parameters, no annotations, but has an output schema), the description is mostly complete. It explains how to trigger the action, but doesn't detail what the App Switcher is or what the output might be, though the output schema may cover return values. For a basic UI command, this is sufficient but not exhaustive.

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 the input schema has 100% coverage (though empty). The description doesn't need to explain parameters, so it appropriately avoids redundant information. A baseline of 4 is applied as it efficiently handles the lack of parameters without unnecessary detail.

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 ('slow swipe up from bottom') and the outcome ('to open the App Switcher'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'go_home' or 'open_control_center', which are also UI navigation actions, so it lacks sibling distinction for a perfect score.

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 doesn't mention scenarios where the App Switcher is needed over other navigation tools or any prerequisites, leaving the agent to infer usage from context 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 provided, the description carries the full burden. It describes the action ('Swipe down') but lacks details on behavioral traits like whether this requires specific device states, if it's reversible, or what happens if Control Center is already open. It provides basic operational context but misses deeper behavioral disclosure.

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

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

The description is a single, efficient sentence that front-loads the essential action and target. There is zero wasted verbiage, and every word earns its place by directly contributing to understanding the tool's purpose.

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

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

Given the tool's simplicity (0 parameters, has output schema), the description is reasonably complete for its purpose. It explains what the tool does clearly, though it could benefit from additional context like device compatibility or expected outcomes, which the output schema might cover.

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 with 100% schema description coverage, so no parameter documentation is needed. The description does not add parameter semantics beyond the schema, but this is appropriate given the lack of parameters, warranting a baseline score above minimum.

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 specific action ('Swipe down') and target resource ('from the top-right to open Control Center'), distinguishing it from siblings like 'open_notification_center' or 'open_app_switcher'. It uses precise terminology that leaves no ambiguity about what the tool does.

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 implicitly provides context for when to use this tool (to open Control Center on a device), but does not explicitly mention when not to use it or name alternatives. It distinguishes from siblings by specifying the Control Center target, though lacks explicit exclusions or comparison to similar 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?

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Swipe down' implies a UI interaction, it doesn't describe what happens after opening (e.g., whether it stays open, what content appears), whether this requires specific device states, or potential side effects. The description is minimal and lacks 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 a single, efficient sentence with zero wasted words. It's appropriately sized for a simple, parameterless action and gets straight to the point without 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 the tool's simplicity (0 parameters, no annotations, but has output schema), the description is minimally adequate. It explains what the tool does but lacks context about when to use it versus siblings and behavioral details. The existence of an output schema means the description doesn't need to explain return values, but it should provide more usage guidance.

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 with 100% schema description coverage, so the schema already fully documents the parameter situation. The description doesn't need to add parameter information, and it appropriately doesn't mention any parameters. Baseline for 0 parameters 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 action ('Swipe down') and target ('Notification Center'), providing a specific verb+resource. However, it doesn't explicitly distinguish this from sibling tools like 'open_control_center' or 'open_app_switcher', which are similar UI navigation 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 doesn't mention when Notification Center is needed versus Control Center or App Switcher, nor does it specify any prerequisites or contextual constraints for this action.

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 describes the action ('Tap') without disclosing behavioral traits like what happens after tapping (e.g., opens a keyboard, triggers a search, requires specific permissions), potential side effects, or error conditions. This leaves the agent with minimal insight into the tool's behavior.

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

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

The description is a single, clear sentence that directly states the action. It's front-loaded with the verb and target, with no wasted words or redundant information. This is appropriately 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?

Given the tool's simplicity (0 parameters, output schema exists), the description is minimal but incomplete. It lacks context on what the tool achieves (e.g., opens a search interface), when to use it, and behavioral details. With no annotations and an output schema that might cover return values, the description should do more to explain the tool's role and effects, but it doesn't.

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%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. Baseline is 4 for zero parameters, as it avoids unnecessary 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?

The description states the action ('Tap') and target ('Search bar on the home screen'), which gives a basic purpose. However, it's vague about what this actually does—does it open a search interface, focus a cursor, or something else? It doesn't clearly distinguish from siblings like 'tap' or 'open_app', which could be used for similar UI interactions.

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

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

No guidance is provided on when to use this tool versus alternatives. For example, it doesn't specify if this is for initiating a search versus other ways to access search functionality, or if it's specific to a certain app or system state. The description is purely instructional without context.

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

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

No annotations are provided, so the description carries full burden. It states the action but doesn't disclose behavioral traits: it doesn't specify if this is a short press or long press, whether it requires device permissions, what happens on different device states (on/off/locked), or potential side effects (e.g., triggering biometric authentication). For a zero-parameter tool with no annotation coverage, this leaves critical behavior ambiguous.

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 a parenthetical clarification that adds necessary context ('lock/wake'). It's front-loaded with the core action and wastes no words. Every part earns its place, making it highly concise and well-structured.

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

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

Given the tool's simplicity (zero parameters, no annotations, but with an output schema), the description is minimally adequate. It states what the tool does but lacks context on usage, behavior, or output. The output schema existence means return values needn't be explained, but for a power button action that could have varied effects, more guidance would improve completeness.

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

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

The tool has zero parameters, and schema description coverage is 100% (though trivial since there are no parameters). The description doesn't need to explain parameters, so it meets the baseline of 4 for zero-parameter tools. No additional parameter semantics are required or provided.

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 target ('power button') with a parenthetical clarification of its function ('lock/wake'). It distinguishes from siblings like volume_up/down or tap by specifying the power button. However, it doesn't explicitly differentiate from all other button/control tools, keeping it from a perfect 5.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention scenarios for pressing the power button (e.g., waking a locked device, putting to sleep) or warn against misuse (e.g., holding too long for shutdown). With siblings like go_home or open_control_center that might serve similar wake/lock purposes in some contexts, this lack of differentiation 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool captures and returns an image, implying a read-only operation without side effects, but lacks details on permissions, rate limits, or error conditions. It adds some context (e.g., 'embedded image that can be analyzed visually') but is not comprehensive for a tool with potential behavioral nuances.

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 highly concise and front-loaded, with two sentences that directly state the action and output. Every sentence earns its place by clarifying the tool's function and return format, with no wasted words or 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 the tool's low complexity (0 parameters, no output schema, no annotations), the description is reasonably complete. It covers the core purpose and output format adequately. However, it could improve by addressing behavioral aspects like error handling or usage constraints, which are relevant even for simple tools.

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

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description does not add parameter semantics beyond the schema, but since there are no parameters, a baseline score of 4 is appropriate as it avoids redundancy and focuses on the tool's purpose.

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 specific action ('Take a screenshot') and resource ('of the VM display'), distinguishing it from sibling tools that perform UI interactions like tapping, scrolling, or opening apps. It precisely defines the tool's function without being vague or tautological.

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 by specifying 'of the VM display,' suggesting it captures the current visual state of a virtual machine. However, it does not explicitly state when to use this tool versus alternatives (e.g., for visual analysis vs. other UI actions), nor does it provide exclusions or prerequisites, leaving some guidance gaps.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. 'Scroll down' implies a UI interaction, but the description doesn't specify what gets scrolled (e.g., content, viewport), how far it scrolls, whether it's animated or instant, or what happens if scrolling isn't possible. This leaves significant behavioral questions unanswered.

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 that communicates the core functionality without any wasted words. It's appropriately sized for a simple, parameterless tool and gets straight to the point.

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 (zero parameters, has output schema), the description is reasonably complete for basic understanding. However, as a UI interaction tool with no annotations, it should ideally provide more behavioral context about what 'scrolling down' entails operationally and what the output represents.

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

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

The tool has zero parameters with 100% schema description coverage, so the schema already fully documents the parameter situation. The description appropriately doesn't add unnecessary parameter information, maintaining focus on the tool's purpose.

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 ('scroll down') and target ('on the current screen'), providing a specific verb+resource combination. However, it doesn't differentiate from its sibling 'scroll_up' beyond the directional difference, which is implied but not explicitly contrasted.

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 like 'swipe' or 'scroll_up', nor does it mention prerequisites or context for scrolling. It simply states what the tool does without indicating 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 provided, the description carries full burden but offers minimal behavioral insight. It doesn't disclose what 'scroll up' entails (e.g., distance, speed, or effect on UI), whether it's idempotent, or potential side effects. The description is functional but lacks depth for informed use.

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 zero wasted words. It's front-loaded with the core action and target, making it highly efficient and easy to parse without 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 the tool's simplicity (0 parameters, output schema exists) and lack of annotations, the description is minimally adequate. However, for a UI interaction tool, it could benefit from more context on behavior (e.g., scroll amount or visual feedback) to fully guide an agent, though the output schema may cover return values.

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 with 100% schema description coverage, so no parameter documentation is needed. The description appropriately avoids redundant parameter details, earning a baseline score above 3 for efficiency in a parameterless context.

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

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

The description clearly states the action ('Scroll up') and target ('on the current screen'), providing a specific verb+resource combination. However, it doesn't differentiate from its sibling 'scroll_down' beyond direction, missing explicit distinction between upward vs downward scrolling.

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

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

No guidance is provided about when to use this tool versus alternatives like 'swipe' or 'scroll_down', nor about contextual prerequisites (e.g., whether a scrollable element must be present). The description only states what it does, not when it's appropriate.

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 mentions coordinate system details and default duration, but doesn't disclose critical behavioral traits: whether this requires specific permissions, if it's destructive (could trigger unintended actions), what happens on invalid coordinates, or what the output schema contains. For a UI interaction tool with zero annotation coverage, this leaves significant gaps.

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 perfectly structured and concise. The first sentence states the core purpose, the second provides essential coordinate context, and the Args section efficiently documents all parameters with clear explanations. Every sentence earns its place with zero 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 5 parameters with 0% schema coverage and no annotations, the description does well on parameter documentation but lacks behavioral context. The presence of an output schema means return values don't need explanation, but for a UI interaction tool that could have side effects, more guidance about permissions, error conditions, or relationship to siblings would improve completeness.

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

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

Schema description coverage is 0%, so the description must fully compensate. It successfully does this by clearly explaining all 5 parameters: defining x1/y1 as start coordinates, x2/y2 as end coordinates, and duration_ms with its default value. The coordinate system context (pixels matching screenshot dimensions) adds crucial meaning beyond the bare schema types.

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: 'Swipe from one point to another' which is a specific verb (swipe) with clear action. It distinguishes from siblings like tap, scroll, or swipe_to_next_page by specifying coordinate-based movement rather than named actions. However, it doesn't explicitly contrast with swipe_to_next_page/swipe_to_previous_page which might be specialized versions.

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 some context about coordinate systems and screenshot dimensions, which implies usage when precise screen coordinates are known. However, it doesn't explicitly state when to use this vs. siblings like swipe_to_next_page or scroll_up/down, nor does it mention prerequisites or alternative scenarios. The guidance is implied rather than explicit.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action but doesn't mention potential side effects (e.g., visual transitions, device state changes), error conditions, or what the output schema might indicate. This is a significant gap for a tool that likely interacts with device UI.

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 that directly states the tool's function without any fluff. It's front-loaded and wastes no words, making it easy to parse quickly.

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 (0 parameters, output schema exists), the description is minimally adequate. However, it lacks context about the home screen environment, potential failures, or how it differs from sibling tools, which reduces completeness 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 tool has 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description doesn't add parameter details, but that's appropriate here. A baseline of 4 is given since it avoids unnecessary repetition.

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 ('swipe left') and the outcome ('go to the next home screen page'), which is specific and unambiguous. However, it doesn't explicitly differentiate from its sibling 'swipe_to_previous_page', which would be needed for a perfect score.

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 like 'swipe' (for general swiping) or 'swipe_to_previous_page'. It lacks context about prerequisites (e.g., being on the home screen) or exclusions, leaving usage unclear.

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 describes the action ('swipe right') and outcome, but doesn't disclose behavioral traits like whether this requires the device to be unlocked, if it works from any screen, or what happens if there's no previous page. It adds basic context 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 a single, efficient sentence that directly states the action and outcome with zero waste. It's appropriately sized and front-loaded, making it easy to understand immediately.

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 (0 parameters, no annotations, but has an output schema), the description is mostly complete. It explains what the tool does, but could benefit from more behavioral context (e.g., prerequisites, limitations). The output schema likely handles return values, reducing the need for that in the description.

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

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate. Baseline is 4 for 0 parameters, as it doesn't need to compensate for any gaps.

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 specific action ('swipe right') and the outcome ('go to the previous home screen page'), distinguishing it from sibling tools like 'swipe_to_next_page' and generic 'swipe'.

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 implicitly indicates this tool is used for navigation between home screen pages, but it doesn't explicitly state when to use it versus alternatives like 'go_home' or 'swipe' with parameters. The context is clear but lacks explicit exclusions or comparisons.

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

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

With no annotations provided, the description carries full burden. It discloses that the action is a 'tap' (implying a touch interaction), specifies coordinate system details (pixels matching 1290x2796 dimensions), and mentions dependency on screenshot() for target identification. It doesn't mention side effects like app responses or timing, but covers core behavioral context adequately.

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?

Perfectly structured: purpose statement first, then coordinate system context, usage guideline, and parameter details. Every sentence earns its place with zero waste. The description is appropriately sized for a simple 2-parameter tool.

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

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

Given the tool's simplicity (2 parameters, no annotations, but has output schema), the description is complete. It explains what the tool does, how to use it, coordinate system, and parameter meanings. With output schema existing, return values needn't be explained in the description.

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

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

Schema description coverage is 0%, so the description must fully compensate. It provides complete parameter semantics: defines x as 'Horizontal pixel coordinate (0=left, 1290=right)' and y as 'Vertical pixel coordinate (0=top, 2796=bottom)', including coordinate system orientation and valid ranges. This adds essential meaning beyond the bare 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 specific action ('Tap at specific pixel coordinates') and resource ('on the screen'), distinguishing it from siblings like swipe, scroll, or button presses. It precisely defines the tool's function without ambiguity.

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

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

Explicit guidance is provided: 'Use screenshot() first to identify the target position.' This tells the agent when to use this tool (after screenshot) and implies an alternative approach for coordinate identification. It also distinguishes from other interaction tools by focusing on precise coordinate-based tapping.

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 describes the action (tap) and target (back button), but doesn't disclose behavioral traits like whether this requires the app to be in a navigable state, what happens if no back button is present, or if there are any side effects. The description adds basic context but lacks richer 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, efficient sentence that immediately states the action and target. Every word earns its place with no redundancy or unnecessary elaboration. It's appropriately sized and front-loaded.

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 (0 parameters, no annotations, but has output schema), the description is reasonably complete. It explains what the tool does, though it could benefit from more behavioral context. The output schema existence means the description doesn't need to explain return values, making it adequate for this low-complexity tool.

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

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

The tool has 0 parameters with 100% schema description coverage. The description doesn't need to explain parameters, and it appropriately doesn't mention any. Baseline for 0 parameters is 4, as there's no parameter information to add 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 specific action ('Tap') and the target resource ('iOS navigation back button') with precise location ('top-left corner'). It distinguishes from siblings like 'go_home' or 'tap' by specifying the exact UI element to interact with.

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 (when navigating iOS apps) but doesn't explicitly state when to use this tool versus alternatives like 'go_home' or 'swipe_to_previous_page'. It provides clear context about the target element but lacks explicit exclusions or named alternatives.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Press volume down' suggests a simple action but doesn't describe effects (e.g., how much volume decreases, whether it's reversible, if it requires specific permissions, or any rate limits). This leaves significant gaps for a mutation-like 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 with 'Press volume down' as a single, front-loaded sentence. It wastes no words and directly conveys the core action, earning full marks for efficiency.

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 (0 parameters, no annotations, but has an output schema), the description is minimally adequate. It states what the tool does but lacks context on behavior, usage, or effects. With no annotations and an output schema that might cover return values, the description should do more to explain the action's impact.

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 with 100% schema description coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here, but it also doesn't compensate for any gaps since there are none. Baseline 4 is applied as per rules for 0 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 'Press volume down' clearly states the action (press) and target (volume down), making the purpose understandable. However, it doesn't differentiate from its sibling 'volume_up' beyond the directional difference, and the purpose is somewhat vague about what system or context this applies to.

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 'volume_up' or other media controls. The description implies usage for lowering volume but doesn't specify context, prerequisites, or exclusions, leaving the agent to infer based on the tool name alone.

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

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

No annotations are provided, so the description carries full burden. It states the action ('Press') but doesn't disclose behavioral traits like whether this is a toggle, incremental step, or one-time press; whether it requires specific permissions; what feedback (if any) is provided; or potential side effects (e.g., audio output changes). The description is minimal and lacks operational 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 extremely concise ('Press volume up.') with no wasted words. It's front-loaded with the core action, making it easy to parse quickly. Every word earns its place by conveying essential information without 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?

Given the tool's simplicity (0 parameters, no annotations, but with an output schema), the description is minimally complete. It states what the tool does but lacks context about behavior, usage, or effects. The output schema may cover return values, but the description doesn't address operational nuances, leaving gaps for an agent to infer.

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%, so there are no parameters to document. The description doesn't need to add parameter semantics beyond what the schema provides, earning a baseline score of 4 for zero-parameter tools as per guidelines.

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 the target ('volume up'), making the purpose immediately understandable. It distinguishes from sibling tools like 'volume_down' by specifying the direction. However, it doesn't specify what device or interface this operates on, which would make it fully specific.

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 doesn't mention prerequisites (e.g., device must be on), context (e.g., only works in certain modes), or explicit alternatives like 'volume_down' or other audio controls. Usage is implied but not articulated.

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