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

No annotations provided; description adds Retina coordinate conversion but lacks details on blocking behavior, failure modes, or off-screen coordinates.

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

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

Two short sentences that state purpose and provide a critical hint, 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?

Simple tool with no output schema; description covers main functionality and coordinate system. Could mention input validation or immediate nature, but adequate.

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

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

Schema covers all 4 parameters with descriptions (100% coverage), and the description adds extra value by clarifying coordinate conversion for Retina displays, which isn't in the schema.

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

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

Clearly states the action 'Click at screen coordinates (in points)' and distinguishes from siblings like move_mouse and click_ui_element by specifying coordinate-based clicking with Retina conversion hint.

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?

Gives practical advice to 'use screenshot to determine positions' but does not explicitly exclude scenarios or mention alternatives like click_ui_element for UI-based clicks.

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 disclose behavioral traits. It only states the basic action without mentioning error handling, element visibility requirements, or whether it scrolls or waits. Minimal 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?

A single 14-word sentence is concise but lacks essential detail for a tool with 4 parameters. It is front-loaded but under-specified for effective use.

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 UI element interaction and the absence of output schema or annotations, the description is incomplete. It does not explain return values, error cases, or how to handle missing elements.

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

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

Input schema covers all 4 parameters with descriptions, so baseline is 3. The description adds no additional meaning beyond what the schema already provides.

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

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

The description clearly states it clicks a named UI element using accessibility, specifying the verb, resource, and method. It distinguishes from coordinate-based 'click' by mentioning accessibility, but does not explicitly differentiate from other interaction 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 alternatives like 'click', 'type_text', or 'get_ui_elements'. The description lacks prerequisites, when-not-to-use, or 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, but the description sufficiently discloses the read-only nature and output format (screen points). No side effects or contradictions.

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

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

Single sentence, front-loaded with key action and resource, no wasted words.

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

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

Given no parameters, no output schema, and simple nature, the description is nearly complete. Lacks explicit return type specification but sufficient for typical 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?

Zero parameters, so baseline is 4. Description adds no parameter info, but none are 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 the verb 'Get' and resource 'current mouse cursor position', specifying units (screen points) to differentiate from sibling tools like move_mouse.

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 cursor coordinates, but provides no explicit context on when to use vs. alternatives, nor any exclusions.

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

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

No annotations are provided, so the description carries full burden. It mentions the 'depth' parameter can be slow for 'deep' but does not disclose other behavioral traits like permissions required, whether data is cached, or impact on the target application. A read-only tool, but no explicit guarantee of non-destructiveness.

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

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

The description is two sentences long, front-loaded with the core function, and the second sentence adds context. No wasted words, but could be more structured (e.g., bullet points for parameter details). Still, it is 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 absence of an output schema, the description should hint at the return format. It does not mention that it returns a tree of elements with properties like role, name, etc. The reference to siblings like click_ui_element provides some context for usage flow, but completeness for a retrieval tool 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?

Schema coverage is 100%, so the schema already documents both parameters. The description adds minimal value: for 'app', it repeats 'application process name', and for 'depth', it adds 'can be slow' to the schema's 'full tree' description. This is marginal improvement, meeting the baseline of 3.

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 'Get accessibility UI elements of a window for a given app', clearly identifying the resource (UI elements of a window) and scope (per app). It distinguishes from sibling tools like click_ui_element, which interacts with elements, and get_mouse_position, which reads mouse coordinates.

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 states it is 'useful for finding buttons, text fields, etc.', implying it is for exploration before interaction. However, no explicit guidance on when not to use or alternatives is provided, though sibling tools suggest context. This is minimally adequate but lacks precise conditions.

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 discloses that it presses keys but doesn't elaborate on potential side effects (e.g., system focus, modifier behavior). However, it's not misleading.

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, efficiently communicates the purpose and example inputs. 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 simplicity of the tool (single parameter, no output schema, no nested objects), the description is complete. It provides all necessary information for an agent to invoke it correctly.

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

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

Only one parameter 'keys' exists, and the schema already describes it with examples. The tool description adds a few more examples (e.g., 'cmd+shift+l'), but adds minimal value beyond the schema. Schema coverage is 100%.

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 key or key combination, with specific examples like 'return', 'escape', 'cmd+c'. This distinguishes it from sibling tools like type_text (which types text) and click (which clicks).

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

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

The description explains when to use the tool (press a key/combination). While it doesn't explicitly exclude alternatives, the sibling context makes it clear. Could be improved by mentioning when type_text might be more 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?

With no annotations, the description must carry the full burden of behavioral disclosure. It only states the action but omits details like whether movement is instant or animated, border behavior, or any side effects. This leaves the agent uncertain about the tool's full impact.

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 superfluous words. However, it omits important details that could be added without sacrificing 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 lack of output schema, annotations, and the presence of sibling tools, the description is too brief. It does not provide essential context such as coordinate system, units, or expected behavior, making it insufficient for an agent to use the tool correctly without additional knowledge.

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 provides basic parameter descriptions ('X coordinate', 'Y coordinate'), and the tool description adds no extra meaning. It does not specify units, coordinate system, valid range, or coordinate origin, leaving significant ambiguity despite 100% schema coverage.

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

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

The description uses the specific verb 'move' and resource 'mouse cursor to given screen coordinates', clearly stating the action and target. It distinguishes this tool from sibling tools like 'click' (which also moves) and 'get_mouse_position' (which reads the position).

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, no prerequisites, and no conditions under which it should not be used. It does not explain the coordinate system (e.g., screen vs. window, origin) or whether coordinates must be within screen bounds.

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 disclose behavioral traits. It only says 'Open and activate' without detailing behavior if the app is already running, how the app is identified (name vs. bundle ID), or potential side effects.

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

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

Single sentence with no wasted words. Front-loaded with the core 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?

The description is adequate for a simple tool with one parameter and no output schema, but it lacks details on error handling, app identification precision, and behavior for non-existing apps.

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

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

Schema coverage is 100% with a parameter description that already includes examples. The tool description does not add significant meaning beyond the schema, though the examples (e.g., 'Slack') are helpful. 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 verb 'Open and activate' and the resource 'macOS application', making it distinct from sibling tools like type_text or move_mouse.

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

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

No guidance on when to use this tool versus alternatives (e.g., run_applescript or click). The description does not specify prerequisites or 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 are provided, so the description carries full burden. It only says 'Run arbitrary AppleScript' without disclosing potential side effects (e.g., destructive actions, security risks, blocking behavior). The agent is left uninformed about execution consequences.

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 with zero wasted words. It is front-loaded with the action and purpose, directly conveying the tool's value.

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?

With only one parameter and no output schema or annotations, the description is too minimal. It omits important context like what the script returns, error handling, security warnings, and prerequisite conditions, which are critical for a tool that executes arbitrary code.

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 already describes 'script' as 'AppleScript code to execute'. The description adds no new meaning beyond that, just rephrases the tool's action. 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 'Run arbitrary AppleScript' (verb+resource) and distinguishes from sibling tools by specifying 'for complex automation that other tools don't cover', indicating it handles cases beyond specific UI automation 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?

Description implies this tool is for tasks not covered by sibling tools like type_text, move_mouse, etc., but does not explicitly state when not to use it or provide direct alternatives. The guidance is clear but 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, the description must disclose all behavioral traits. It reveals that the tool returns an image and a scale factor, and explains how to use the scale factor for coordinate mapping. It does not mention potential permissions (e.g., screen recording) or image format, but the key behavioral nuance is covered.

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

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

The description is two sentences, front-loading the action and providing essential detail efficiently. No extraneous 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 tool is low-complexity. Although there is no output schema, the description adequately explains the return values (image and scale factor) and their usage. It lacks details on image format or resolution, but this is not critical for basic usage.

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 single parameter 'app' is well-documented in the schema (100% coverage). The description adds no additional meaning beyond the schema description, 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 'Take a screenshot of the entire screen or a specific app window', specifying the action and resource. It distinguishes from sibling tools (none are screenshot-related).

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

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

The description explains when to use the optional 'app' parameter ('If omitted, captures full screen'), providing clear conditional usage. No explicit exclusions or alternatives are given, which is acceptable for a simple 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, and the description only states basic behavior. It does not disclose whether scrolling is smooth or discrete, whether it triggers events, or what happens if coordinates are out of bounds. The description carries the full burden but is insufficient.

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. It is efficient, though could benefit from a touch more detail without becoming verbose.

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

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

Given no annotations, no output schema, and siblings that are UI interaction tools, the description lacks important context such as whether a window must be focused, what scrolleable elements it works on, and any side effects. It is incomplete for reliable agent invocation.

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

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

Input schema has 100% coverage with descriptions for all 4 parameters. The tool description adds little beyond the schema, only clarifying that x and y are for coordinates to scroll at. Baseline 3 is appropriate as the description does not significantly enhance parameter 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 identifies the action (scroll) and the target (mouse position or coordinates). It distinguishes the tool from siblings by focusing on scrolling, but could be more specific about what is being scrolled (e.g., active window or content under cursor).

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 move_mouse, click, or keyboard actions. It does not mention prerequisites or limitations.

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?

Lacks annotations, so description must carry behavioral information. It mentions 'frontmost app receives input' but omits details about special characters, latency, or error handling.

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

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

Two concise sentences, front-loaded with the core action, 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?

For a simple tool with one parameter and no output schema, the description is mostly complete, though could mention return behavior or side effects.

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 description adds no new meaning beyond the schema's 'Text to type' description. Baseline 3 applies.

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?

Clearly states 'Type text using the keyboard' with a specific verb and resource, and distinguishes from sibling tools like key_press which handles key combos.

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 key_press or click_ui_element. Agent must infer from name and description alone.

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