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. It states the tool captures and saves a screenshot, implying a read-only operation that creates a file, but it doesn't disclose critical details such as file format, permissions needed, whether it overwrites existing files, error conditions, or any side effects. This leaves significant gaps for an agent to understand 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, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded, making it easy to understand at a glance.

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

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

Given the complexity of a screenshot tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral aspects (e.g., file handling, errors), usage context, and output information, which are essential for an agent to use the tool effectively in a testing environment with multiple sibling 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?

Schema description coverage is 100%, with clear descriptions for both parameters in the input schema. The description adds no additional meaning beyond what the schema provides, as it doesn't explain parameter relationships or usage examples. However, with high schema coverage, a baseline score of 3 is appropriate since the schema adequately documents the parameters.

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

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

The description clearly states the action ('capture a screenshot') and the outcome ('save it to the test folder'), providing a specific verb+resource combination. However, it doesn't explicitly distinguish this tool from sibling tools like 'capture_ui_dump' or 'create_test_folder', which might have overlapping purposes in a testing context.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an active app or test folder), exclusions, or how it relates to siblings like 'capture_ui_dump' for different types of captures or 'create_test_folder' for folder setup.

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 what the tool does but doesn't describe behavioral traits such as whether it requires device connectivity, if it's read-only or has side effects, latency expectations, or output format. For a tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, clear sentence with no wasted words. It's front-loaded with the core purpose and efficiently communicates the essential action without unnecessary elaboration, 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 lack of annotations and output schema, the description is incomplete for a tool that likely interacts with device UI. It doesn't explain what a 'UI hierarchy dump' entails, how the output is structured, or any behavioral context (e.g., device requirements). For a tool with no structured data support, the description should provide more 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 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't add parameter details beyond what the schema provides, earning a baseline score of 4 for tools with 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 ('capture') and resource ('UI hierarchy dump from the device'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'capture_screenshot' (which likely captures visual output rather than hierarchy data), leaving room for improvement in sibling distinction.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context (e.g., device state), or comparisons to siblings like 'capture_screenshot' or 'list_apps', leaving the agent to infer usage scenarios without explicit direction.

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 tool creates a folder, implying a write/mutation operation, but doesn't disclose behavioral traits like permissions needed, whether it overwrites existing folders, error handling, or what happens upon success. This is a significant gap for a mutation tool with zero annotation coverage.

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 waste. It's front-loaded with the core action and resource, 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 this is a mutation tool with no annotations, no output schema, and incomplete behavioral disclosure, the description is inadequate. It lacks details on what the tool returns, error conditions, or how it integrates with sibling tools (e.g., for testing workflows), leaving the agent with insufficient context for reliable use.

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 the parameter 'test_name' fully documented in the schema. The description adds minimal value beyond the schema by implying the name is used for folder creation, but doesn't provide additional context like naming constraints or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Create') and resource ('test folder'), specifying it creates a folder with a given name. It distinguishes from siblings like capture_screenshot or input_text by focusing on folder creation, though it doesn't explicitly differentiate from other potential folder-related tools (none listed).

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

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

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, context (e.g., for testing purposes), or exclusions, leaving the agent to infer usage from 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 ('Send key events') but doesn't disclose behavioral traits like whether this requires device permissions, if it's synchronous/asynchronous, what happens on failure, or if it affects app state. For a mutation tool with zero annotation coverage, this is a significant gap.

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 and front-loaded with a single, clear sentence. Every word earns its place by specifying the action and key examples without redundancy. No structural issues.

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

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

Given one parameter with full schema coverage and no output schema, the description is minimally adequate. It states the purpose but lacks context on usage guidelines, behavioral transparency, or integration with siblings. For a simple tool, it's functional but could be more helpful.

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

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

Schema description coverage is 100%, with the schema fully documenting the single 'key' parameter (type, enum, description). The description lists the enum values but adds no meaning beyond what the schema provides, such as context for when to use each key. Baseline 3 is appropriate when schema does the heavy lifting.

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 ('Send') and resource ('key events') with specific examples (BACK, HOME, ENTER, DELETE). It distinguishes from siblings like input_tap or input_text by focusing on discrete key events rather than taps or text input. However, it doesn't explicitly differentiate from all siblings (e.g., input_scroll might also involve navigation).

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

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

No explicit guidance on when to use this tool versus alternatives. The description implies usage for sending specific key events, but doesn't mention when to choose this over input_tap for navigation or input_text for text entry. No prerequisites or exclusions are 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Perform scroll action' implies a mutation (scrolling changes viewport position), but it doesn't specify if this requires permissions, has side effects (e.g., triggering UI updates), or details on execution (e.g., smooth vs. instant scroll). The description is too minimal to convey behavioral traits beyond the basic action.

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

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

The description is extremely concise with a single sentence 'Perform scroll action', which is front-loaded and wastes no words. It efficiently states the core action without redundancy, making it easy to parse quickly. This minimalism is appropriate for a simple tool, though it may sacrifice 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?

Given the tool's simplicity (1 parameter, no output schema, no annotations), the description is incomplete. It doesn't cover what the tool scrolls (e.g., a screen or element), behavioral aspects like side effects, or usage context relative to siblings. For a mutation tool with no annotations, more detail is needed to ensure the agent can use it correctly without guesswork.

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

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

The input schema has 100% description coverage, with the parameter 'direction' fully documented via enum values ('up', 'down', 'left', 'right'). The description adds no meaning beyond the schema, as it doesn't explain parameter usage (e.g., how direction relates to UI orientation) or constraints. With high schema coverage, the baseline score of 3 is appropriate, as the schema does the heavy lifting.

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

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

The description 'Perform scroll action' states a verb ('Perform') and resource/action ('scroll action'), making the purpose identifiable but vague. It doesn't specify what is being scrolled (e.g., a UI, webpage, or viewport) or distinguish it from sibling tools like 'input_tap' or 'input_keyevent', which are also input actions. The purpose is clear at a high level but lacks specificity for precise tool selection.

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 context (e.g., scrolling in an app vs. a webpage), prerequisites, or exclusions. With siblings like 'input_tap' and 'input_keyevent' for other input types, the agent must infer usage based on the tool name alone, which is insufficient for informed 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?

With no annotations provided, the description carries full burden but only states the basic action. It doesn't disclose behavioral traits such as whether the tap is immediate, if it requires specific permissions, what happens if coordinates are invalid, or if there are rate limits. This leaves significant gaps for a mutation 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 a single, front-loaded sentence that directly states the tool's function. There is zero wasted language, making it efficient and easy to parse.

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

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

Given the tool's complexity (a mutation with no annotations or output schema) and the description's minimalism, it's incomplete. It lacks details on behavior, error handling, or integration with sibling tools, leaving the agent with insufficient context for reliable use.

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 description coverage is 100%, with both parameters (x and y) documented in the schema. The description adds no additional meaning beyond implying coordinate-based input, so it meets the baseline of 3 where the schema does the heavy lifting.

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 'Tap at specific coordinates' clearly states the action (tap) and target (specific coordinates), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like input_keyevent or input_scroll, which are also input actions but with different modalities.

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 input_keyevent or input_text. There's no mention of context (e.g., for UI interaction vs. text entry) or prerequisites (e.g., needing an app open).

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 states the action ('input text') but doesn't disclose whether this requires specific conditions (e.g., an active field), how it handles errors, or what the expected outcome is. This is inadequate for a mutation tool with zero annotation coverage.

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 waste—'Input text into the current field' is front-loaded and appropriately sized for a simple tool. Every word earns its place, 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 (1 parameter, 100% schema coverage) but lack of annotations and output schema, the description is incomplete. It doesn't address behavioral aspects like what 'current field' means, potential side effects, or error handling, which are crucial for an input mutation 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?

Schema description coverage is 100%, with the single parameter 'text' well-documented in the schema as 'Text to input'. The description adds no additional meaning beyond this, such as format constraints or examples, so it meets the baseline of 3 where the schema does the heavy lifting.

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 'Input text into the current field' clearly states the action (input) and target (current field), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'input_keyevent' or 'input_tap' that also perform input operations but with different methods.

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 'input_keyevent' for keyboard events or 'input_tap' for touch inputs. It lacks any context about prerequisites (e.g., needing a field to be focused) or exclusions, leaving usage entirely implicit.

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 'List' implies a read-only operation, it doesn't specify what 'matching' entails (exact match, substring, regex), whether results are filtered/limited, what format the output takes, or any performance/rate considerations. The description provides minimal behavioral context beyond the basic operation.

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 tool with one parameter and gets straight to the point with clear front-loaded information.

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

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

For a tool with no annotations and no output schema, the description is insufficiently complete. It doesn't describe what the output looks like (list format, fields included), any limitations on results, error conditions, or how the pattern matching works. The agent would need to guess about important behavioral aspects of this 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?

Schema description coverage is 100% with the parameter 'app_name' fully documented in the schema. The description adds the context that this is a 'name pattern to search for in app packages,' which slightly elaborates on the schema's description. However, it doesn't provide additional syntax examples, format details, or constraints beyond what the schema already 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 clearly states the verb ('List') and resource ('installed apps') with the specific action of matching a name pattern. It distinguishes from obvious siblings like 'open_app' by focusing on listing/searching rather than launching apps. However, it doesn't explicitly differentiate from other potential list/search tools that might exist.

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, limitations, or compare with other search/list tools. The agent must infer usage from the name and description alone without explicit 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?

With no annotations, the description carries full burden but lacks behavioral details. It doesn't disclose if this requires specific permissions (e.g., accessibility services), whether it launches in foreground/background, error handling (e.g., if app isn't installed), or side effects (e.g., interrupting current tasks). 'Open' implies a mutation, but safety and operational context 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, efficient sentence with zero waste. It's front-loaded with the core action and uses clear terminology. Every word earns its place, 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?

For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavior, error cases, or return values (e.g., success/failure indicators). Given the complexity of opening apps (which can fail or have side effects), more context is needed for safe and effective use.

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 the parameter 'package_name' fully documented in the schema. The description adds minimal value by mentioning 'package name and activity' (though 'activity' isn't a parameter), but doesn't clarify semantics beyond the schema. Baseline 3 is appropriate as the schema does the heavy lifting.

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 ('Open') and target resource ('an app') with the mechanism ('using its package name and activity'). It distinguishes from siblings like 'list_apps' (which enumerates) and input tools (which interact with already-open apps). However, it doesn't explicitly contrast with all siblings, missing 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?

No guidance on when to use this tool versus alternatives is provided. It doesn't mention prerequisites (e.g., app must be installed), when not to use it (e.g., for web apps), or alternatives like using 'input_tap' on an app icon. The description only states what it does, not when to apply it.

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