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

The description does not add behavioral context beyond the destructiveHint annotation. It does not mention side effects, prerequisites, or error states. With the annotation already indicating destructiveness, the description is adequate but not enhanced.

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 with no redundancy. The purpose is front-loaded, and every sentence adds 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?

For a simple click tool with annotations and full schema, the description is nearly complete. It lacks details on coordinate validation and return values, but these are implied. Slightly more differentiation from sibling tools 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 coverage is 100% with clear parameter descriptions. The description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.

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

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

The description clearly states the action (clicking) and the resource (screen at coordinates). It suggests an alternative tool (list_elements_on_screen) for element-based clicks, but does not differentiate from sibling tools like double-tap or long-press at 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?

Provides explicit guidance: use list_elements_on_screen to find coordinates when clicking on an element. However, it does not specify when not to use this tool or mention alternatives for similar actions.

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

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

Annotations already indicate destructiveHint=true, so the description does not need to repeat that. However, it adds no additional behavioral context beyond the annotation, such as potential side effects or system response. This is adequate but not exceptional.

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

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

The description is very short (one sentence) and front-loaded with the key action. It is efficient, though it could be slightly expanded to add value without losing conciseness.

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

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

Given the simple nature of the tool (no output schema, 3 parameters), the description is minimally complete. However, it lacks details about coordinate system (e.g., absolute/relative) or any side effects, making it somewhat incomplete for an agent to fully understand behavior.

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

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

Schema coverage is 100%, meaning all parameters already have descriptions. The tool description adds no extra meaning beyond what is in the schema, so it is baseline adequate.

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 (double-tap) and the resource (screen at x,y coordinates). It effectively distinguishes from sibling tools like mobile_click_on_screen_at_coordinates (single tap) and mobile_long_press_on_screen_at_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 provides no guidance on when to use this tool versus alternatives, nor any context about prerequisites, exclusions, or typical use cases. It simply states what it does.

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

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

Annotations declare readOnlyHint=true. Description adds 'full content' detail but no additional behavioral traits beyond what annotations imply. For a simple read, this is adequate but not exceptional.

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: first states purpose, second provides usage guideline. No filler words, front-loaded with key action.

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

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

With only 2 parameters, no output schema, and readOnlyHint, the description fully covers the tool's purpose and usage context. Input schema provides complete parameter documentation.

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 both parameters ('device' and 'id') with descriptions. The description does not add extra meaning beyond schema, so 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?

Description clearly states 'Get the full content of a crash report by its ID.' Uses specific verb 'get' and resource 'full content of a crash report', distinguishing it from sibling tool 'mobile_list_crashes' which only lists IDs.

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

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

Explicitly directs to use 'mobile_list_crashes to find available crash IDs', providing a clear prerequisite. Lacks explicit 'when not to use' but the single-purpose nature makes it sufficient.

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

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

Annotations already declare readOnlyHint: true. The description adds no additional behavioral context (e.g., permissions, rate limits) beyond what is obvious from the verb 'get'.

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, front-loaded with the essential information. 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 read-only tool with one parameter and no output schema, the description covers all needed information. The schema handles parameter details adequately.

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

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

Schema description coverage is 100%, so the parameter 'device' is well-documented in the schema. The tool description does not add any extra meaning beyond what the schema provides.

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

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

The description clearly states the action ('get') and the resource ('current screen orientation'). This distinguishes it from sibling tools like mobile_set_orientation, which sets the orientation.

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 when to use it (to read orientation) but does not explicitly mention alternatives like mobile_set_orientation or provide when-not-to-use guidance. For a simple tool, this is adequate but lacks 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?

Annotations already indicate readOnlyHint=true, so the agent knows this is a safe read operation. The description adds no further behavioral context, such as what the return format is (e.g., width x height) or if any side effects occur. Given the annotation, a score of 3 is appropriate as the description doesn't contradict but also doesn't add value.

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

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

The description is a single sentence of 11 words that directly states the purpose. No fluff, no repetition. It is concise 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 (one parameter, no output schema), the description is mostly complete. However, it could mention that the return value is width and height in pixels to avoid ambiguity. Still, for a basic getter, this is sufficient.

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

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

The input schema covers the only parameter 'device' with a description that tells the user to use mobile_list_available_devices to find valid identifiers. Since schema description coverage is 100%, the description doesn't need to add more. It adds marginal value beyond the schema.

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

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

The description clearly states the tool's purpose: retrieving the screen size of a mobile device in pixels. It uses a specific verb ('Get') and resource ('screen size'), and it distinguishes itself from sibling tools that perform actions like clicking, swiping, or getting orientation.

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. For instance, it doesn't mention that this tool might be a prerequisite for coordinate-based actions, nor does it explain when not to use it. There is no explicit context or exclusion.

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

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

The description does not add any behavioral context beyond the 'destructiveHint' annotation (which already indicates a destructive operation). It omits information about permissions, potential failures, or 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?

The description is a single, front-loaded sentence with no wasted words. It is concise but could be more informative without sacrificing brevity.

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 has two well-documented parameters and no output schema. The description is minimal and does not explain return values, installation time, or post-installation behavior. It is adequate for a straightforward operation but lacks 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 100% description coverage, detailing 'device' usage and 'path' file types. The description adds no extra meaning, so a 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 uses a clear verb+resource structure: 'Install an app on mobile device'. It distinguishes from siblings like 'mobile_launch_app' (launch an installed app) and 'mobile_uninstall_app' (remove an app). However, it could be more specific about the installation process (e.g., from a file).

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

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

The description provides no guidance on when to use this tool versus alternatives, such as when the app is already installed or needs to be launched. No exclusions or prerequisites are mentioned.

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

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

Annotations already declare destructiveHint=true, indicating state change. Description does not add behavioral details (e.g., whether it brings app to foreground, or requires specific permissions). With annotations, this is adequate but not enhanced.

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

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

Two sentences, front-loaded, no wasted words. Every sentence adds value: purpose and usage guidance.

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 destructiveHint annotation, but description lacks info on result (e.g., success/failure, returning control). No output schema, so some explanation of outcome 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 coverage is 100% with descriptions for all 3 parameters. Tool description adds no extra meaning beyond the schema, so baseline of 3 is appropriate.

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

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

Clearly states 'Launch an app' with specific verb and resource. Distinguishes from siblings like mobile_open_url and mobile_install_app by focusing on opening an already-installed app.

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

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

Explicitly says 'Use this to open a specific app' and provides a prerequisite (find package name via list_apps_on_device). No exclusions or direct alternatives, but context is sufficient.

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

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

Annotations declare readOnlyHint=true, so the description doesn't need to emphasize safety. It adds context that the tool lists installed apps, but doesn't disclose any potential side effects or permissions required, which is acceptable given the annotations.

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

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

The description is a single sentence, front-loaded with the core purpose, and contains no unnecessary words. It is efficient and direct.

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

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

For a simple tool with one parameter and no output schema, the description adequately explains the purpose and parameter usage. However, it does not specify the format or content of the returned list, which would be beneficial for a read-only 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 coverage is 100% and the description adds no additional meaning beyond what the schema provides. The device parameter is documented clearly in the schema, referencing the sibling tool for device discovery.

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 lists installed apps on the device, using specific verb+resource. It distinguishes from siblings like mobile_install_app, mobile_uninstall_app, and mobile_launch_app.

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 clear context for when to use the tool, but lacks explicit exclusions or alternatives. The sibling tool mobile_list_available_devices is referenced for the device parameter, offering some 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?

Annotations already declare readOnlyHint=true, so the tool's safety is known. The description adds value by detailing what is returned (physical and simulator/emulator devices, both OS types), which is helpful beyond the annotation.

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

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

Two concise sentences that front-load the core action and add necessary details. 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?

The description covers what the tool returns (device types and OS), which is sufficient for a simple list tool. However, it could mention what fields (e.g., device ID or name) are in the output, but this is a minor gap.

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

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

The tool has no parameters and the input schema is empty (100% coverage). With 0 parameters, the baseline is 4, and no additional parameter info is needed.

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

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

The description clearly states the verb 'List' and the resource 'available devices,' and specifies it includes physical and simulated/emulated devices of both Android and iOS. This distinguishes it from sibling tools which are action-oriented (e.g., click, install).

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

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

The description implies usage for discovering available devices before using other mobile tools. While no explicit when-not-to-use or alternatives are provided, the context from sibling tool names makes the tool's role clear.

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

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

Annotations already declare readOnlyHint=true, so the description adds no essential behavioral detail beyond confirming it's a read operation. No contradictions.

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

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

One sentence, no filler. Efficiently communicates the core purpose.

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

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

For a simple listing tool with good schema coverage and annotations, the description is nearly complete. Could mention output format, but not critical given low complexity.

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

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

Schema coverage is 100% and the description does not add meaning beyond what the schema already provides for the 'device' parameter. Baseline score 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?

The description clearly states the action ('List') and the resource ('crash reports on the device'), with a specific verb+resource pattern that distinguishes it from siblings like mobile_get_crash.

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 mobile_get_crash. The parameter description hints at using mobile_list_available_devices first, but no broader usage 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?

Annotations already indicate readOnlyHint=true, and the description adds the behavioral note about not caching results, which provides context beyond the annotation. No contradictions.

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

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

Two sentences, front-loaded with the purpose, followed by a crucial usage note. No extraneous 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?

Given the simple one-parameter input, the description covers the return values and provides a caching caveat. No output schema exists, but the description sufficiently indicates what is returned.

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

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

Schema coverage is 100% and the schema parameter descriptions are already clear (e.g., referencing mobile_list_available_devices). The description does not add additional parameter semantics beyond what the schema provides.

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

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

The description clearly states the verb 'list' and the resource 'elements on screen,' and specifies the returned information (coordinates, display text or accessibility label). It distinguishes itself from sibling tools like mobile_click_on_screen_at_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 includes a note 'Do not cache this result,' which is a usage guideline, but it does not specify when to use this tool versus alternatives or provide explicit exclusions.

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

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

Annotations indicate destructiveHint=true, but description does not elaborate on potential effects. However, it adds useful context about coordinate-based action vs element-based. No contradiction.

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 deliver core purpose and a key usage tip. No fluff.

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

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

Lacks explanation of result (e.g., what happens after long press) or edge cases, but for a simple action, the description suffices.

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 parameters with descriptions. Description adds cross-reference to list_elements_on_screen for finding coordinates, which is helpful beyond 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 'Long press on the screen at given x,y coordinates', specifying the verb and resource. Differentiates from siblings like mobile_click_on_screen_at_coordinates by explicitly mentioning long press.

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

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

Explicitly advises using list_elements_on_screen tool to find coordinates when pressing on an element, providing clear when-to-use and when-not-to-use 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?

Annotations provide destructiveHint: true, which already signals potential side effects. The description adds no extra context about behavior beyond the obvious action. It does not mention whether a browser must be installed, if the URL will replace current content, or what happens on failure.

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, front-loaded sentence of 8 words with no extraneous information. Every word earns its place, providing clarity without verbosity.

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

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

While annotations and schema cover basic safety and parameter info, the description lacks details like required permissions (e.g., internet access), dependencies on installed browsers, or behavior if the device is locked. For a simple action, this may suffice but leaves gaps.

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

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

Schema coverage is 100% and includes helpful descriptions: the device parameter explicitly directs to use mobile_list_available_devices, adding value beyond the parameter name. The url parameter description is basic but sufficient.

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', the resource 'URL', and the context 'in browser on device'. Among sibling tools, none other perform URL opening, making it immediately distinguishable.

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., using mobile_launch_app for a browser, or mobile_click to navigate). No prerequisites or exclusions are mentioned, leaving the agent to infer usage 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?

Annotations already indicate destructiveHint: true, so the description does not need to repeat that. The description adds no further behavioral details (e.g., effect on app state, permissions required). It is consistent with annotations but provides no extra value beyond them.

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

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

The description is very concise (one short sentence) and front-loaded with the core action. It does not waste words, though it could be slightly expanded to include context 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 that there is no output schema and the tool is destructive (destructiveHint true), the description lacks details about return values, side effects, or prerequisites. For a simple tool with only two parameters, it is minimally adequate but leaves out important contextual information.

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

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

The input schema provides 100% coverage with descriptions for both parameters. The tool description adds no additional meaning beyond the schema. Per guidelines, baseline is 3 when schema coverage is high.

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 a button on device' clearly states the action and resource. It effectively distinguishes from sibling tools like mobile_click_on_screen_at_coordinates or mobile_type_keys by specifying a physical button press. However, it could be slightly more specific about the context (e.g., hardware vs software buttons).

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 does not mention prerequisites, conditions, or when not to use it. Given the sibling tools, explicit usage guidelines would help the agent decide correctly.

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

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

Annotations already declare destructiveHint=true, indicating the tool modifies state (likely overwrites files). The description does not elaborate on what exactly is destroyed (e.g., existing files at saveTo path) or any side effects beyond the annotation.

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

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

The description is a single sentence that is front-loaded with the key action and resource. Every word contributes meaning; no unnecessary content.

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 two-parameter tool with full schema coverage and a destructive annotation, the description provides adequate context. However, it omits details about overwrite behavior, error conditions, or file format validation that 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 100% with both parameters documented. The description adds no additional meaning beyond the schema, so baseline score of 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?

The description clearly states the action ('Save a screenshot') and the resource ('mobile device to a file'), distinguishing it from sibling tools like 'mobile_take_screenshot' which likely returns the image data rather than saving to file.

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 explicit guidance on when to use this tool versus alternatives like 'mobile_take_screenshot'. The schema hints to use 'mobile_list_available_devices' for the device parameter, but no context about 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?

Annotations include destructiveHint=true, so the description should elaborate on potential side effects. It merely says 'change the screen orientation', which is accurate but lacks detail on consequences (e.g., app rotation, possible disruption). The description adds minimal value beyond the annotation.

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

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

The description is a single, well-structured sentence that efficiently conveys the tool's purpose without superfluous 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 two-parameter tool, the description provides basic functionality but lacks usage context. Given the many sibling tools, the agent would benefit from guidance on when to set orientation. The description is minimally complete but not comprehensive.

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 both parameters having clear descriptions. The tool description does not provide additional semantic value beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the action ('Change ... orientation') and the resource ('screen orientation'). While it doesn't explicitly differentiate from siblings like mobile_get_orientation, the verb 'set' versus 'get' is implied and the title reinforces it.

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

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

The description provides no guidance on when to use this tool versus alternatives (e.g., mobile_get_orientation) or any prerequisites (e.g., device state). This is a significant gap for an agent deciding between sibling tools.

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

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

Annotations already set destructiveHint=true. The description adds behavioral details: recording runs in background, returns save path, and implies a persistent file. It does not contradict annotations.

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

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

Three concise sentences with front-loaded purpose. Every sentence adds value: what it does, background behavior, stop instruction, and return value. No redundancy.

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

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

For a start-recording tool, the description covers all key aspects: action, background execution, stop counterpart, and return value. No output schema is needed given the simplicity.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no additional parameter details 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 starts screen recording on a mobile device, uses a specific verb ('Start recording'), and implicitly distinguishes from siblings like 'mobile_take_screenshot' (still image) and 'mobile_stop_screen_recording' (stop counterpart).

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 the recording runs in the background until stopped by 'mobile_stop_screen_recording', providing clear usage context. It does not list explicit alternatives but the sibling set makes the differentiation clear.

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

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

Annotations already indicate destructiveness (destructiveHint=true). The description adds that it returns file path, size, and duration. It does not mention error handling if no recording is active, but the core behavior is clear.

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 well-structured sentences: first sentence states action, second states return. No wasted words and information is 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?

The description explains the return values (file path, size, duration) and parameter usage. However, it does not mention prerequisites (e.g., recording must be active) or error conditions, which would be helpful for 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 only parameter 'device' is described as referencing mobile_list_available_devices for available options. Schema coverage is 100%, but the description adds helpful cross-reference 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 ('stop'), the resource ('active screen recording'), and the return values ('file path, size, and approximate duration'). It is specific and distinct from siblings like mobile_start_screen_recording.

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 it should be used after starting a recording, but does not explicitly state when to use or when not to use. No alternatives are mentioned, but the single tool for stopping recording makes it adequate.

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

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

The description does not mention its destructive nature (annotations indicate destructiveHint: true), nor any behavioral details like system gestures (e.g., edge swipes), duration, or acceleration. The annotations partially cover safety, but the description adds no behavioral context beyond the bare 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 consists of a single short sentence, which is concise but overly sparse. It sacrifices useful detail for brevity, making it insufficient for an agent to fully understand the tool's behavior.

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

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

Given the destructive hint, a more informative description is warranted to explain potential consequences (e.g., triggering system gestures, causing navigation). There is no output schema, so the description should clarify return values or side effects. The current text is inadequate.

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

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

The input schema has 100% description coverage, so the schema already documents each parameter well (e.g., device, direction, optional x/y/distance). The description adds no extra meaning; it is merely a short phrase that repeats the tool name.

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 'Swipe on the screen' is a near-tautology of the tool name and title, providing minimal insight. It does not specify the effect (e.g., scrolling, navigation) or distinguish from sibling tools like mobile_click_on_screen_at_coordinates or mobile_long_press_on_screen_at_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 offers no guidance on when to use this tool versus alternatives. For example, it does not explain that swiping is for scrolling or gestures, while clicking or tapping is for selecting elements. The presence of many sibling tools makes this omission significant.

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

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

The annotation already indicates readOnlyHint=true, which is consistent. The description adds a behavioral note ('Do not cache this result') that goes beyond the annotation. However, it does not detail any potential side effects or specifics about the screenshot capture (e.g., full screen vs. viewport, but given simplicity, a 4 is appropriate.

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

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

The description is extremely concise with two sentences, both front-loaded with key information. Every sentence adds value 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?

For a simple tool with one required parameter, no output schema, and clear annotations, the description provides complete guidance on when to use, what it does, and a behavioral note. No further information is necessary.

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

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

The input schema has 100% coverage with a detailed description for the device parameter, so the description does not need to add more. It meets the baseline expectation.

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

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

The description clearly states the action ('Take a screenshot') and the resource ('mobile device'), and it distinguishes itself from sibling tools like 'mobile_list_elements_on_screen' by explicitly stating when to use that alternative instead.

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 clear usage context: use to understand what's on screen, and explicitly states when not to use it (if you need to press an element from the view hierarchy) and what to use instead (list elements on screen).

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

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

The destructiveHint annotation already signals mutation. The description 'Stop and terminate' aligns with this but adds no additional context (e.g., whether it kills the process, clears app state, or requires permissions). With the annotation, the description is minimally adequate.

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

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

A single, clear sentence that directly states the tool's purpose without any unnecessary words. Appropriate length for a simple operation.

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 2 required parameters, full schema coverage, and presence of destructiveHint annotation, the description is functional but minimal. It could be improved by noting that the app is not uninstalled and that this is distinct from other operations.

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

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

Input schema has 100% description coverage for both parameters (device, packageName). The description adds no extra meaning beyond the schema, so 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?

The description 'Stop and terminate an app on mobile device' uses a specific verb-resource pair (stop/terminate, app) and clearly distinguishes it from sibling tools like mobile_launch_app (launch) and mobile_uninstall_app (remove).

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., mobile_uninstall_app or simply closing the UI). There is no mention of prerequisites, side effects, or when not to use it.

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

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

The description does not add behavioral context beyond the annotation destructiveHint=true. No mention of what happens with submit parameter or typing mechanics.

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, front-loaded sentence with no redundant information. Perfectly concise.

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

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

Minimal description lacks context about prerequisites (focused element), behavior when no element is focused, or typing mechanics. Adequate but with gaps.

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

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

The input schema already provides full descriptions for all three parameters (device, text, submit). The description adds no additional semantic value.

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 'Type text into the focused element', specifying the action and target. It is distinct from sibling tools like mobile_press_button or mobile_click_on_screen_at_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?

No guidance on when to use this tool versus alternatives, nor any prerequisites like ensuring an element is focused. Missing context for effective selection.

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

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

The annotation already signals destructiveness via destructiveHint=true. The description adds no behavioral context beyond acknowledging the action, which is consistent. However, it could elaborate on effects (e.g., data removal) but is not required given the annotation.

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

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

A single, front-loaded sentence that conveys the core purpose without 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?

For a simple destructive tool with clear schema and annotations, the description is largely adequate. It could mention the absence of output schema, but the action's outcome is implied.

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

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

The input schema has 100% coverage with descriptions for both parameters. The tool description adds no additional detail beyond the schema, meeting the baseline.

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 'Uninstall' and the resource 'app from mobile device', distinguishing it from sibling tools like mobile_install_app.

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 or not use this tool versus alternatives. The input schema hints at using mobile_list_available_devices but does not provide context for when uninstalling is appropriate.

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