Server Quality Checklist

Tool Scores

• mobile_clickC
  2.9/5.0
  Behavior2/5

  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 mentions clicking but doesn't specify whether this requires the device to be unlocked, if it's a simulated or physical click, potential side effects, or error conditions. This leaves significant gaps for a tool that interacts with a mobile interface.

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

  Conciseness4/5

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

  The description is efficiently structured with a clear purpose statement followed by parameter explanations. Both sentences earn their place, though it could be slightly more front-loaded by integrating parameter hints into the main description.

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

  Completeness3/5

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

  Given the tool's moderate complexity (interactive mobile action) and the presence of an output schema (which handles return values), the description covers the basic purpose and parameters. However, with no annotations and incomplete behavioral context, it's adequate but has clear gaps in usage and operational details.

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

  Parameters3/5

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

  The schema description coverage is 0%, but the description explicitly documents both parameters (x and y) and their purpose as coordinates. This adds meaningful context beyond the bare schema, though it doesn't specify coordinate systems, units, or valid ranges, keeping it at a baseline level.

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

  Purpose4/5

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

  The description clearly states the action ('Click on') and target ('a specific coordinate on the Android screen'), providing a specific verb+resource combination. However, it doesn't explicitly distinguish this from sibling tools like mobile_swipe or mobile_tap, which might have similar coordinate-based interactions.

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

  Usage Guidelines2/5

  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 mobile_swipe or mobile_tap, nor does it mention prerequisites such as needing mobile_init first or context about screen coordinates. It only states what the tool does, not when it's appropriate.

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

• mobile_key_pressC
  2.9/5.0
  Behavior2/5

  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 mentions pressing buttons but doesn't cover critical aspects like required device state, permissions, side effects, or error handling. This is a significant gap for a tool that likely interacts with an Android device.

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

  Conciseness4/5

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

  The description is front-loaded with a clear purpose statement, followed by parameter examples in a structured Args section. It's efficient with minimal waste, though it could be slightly more concise by integrating the Args into the main text.

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

  Completeness3/5

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

  Given the tool's moderate complexity (interacting with an Android device), no annotations, and an output schema present, the description is somewhat complete but lacks details on behavioral context and usage guidelines. The output schema reduces the need to explain return values, but more device-specific info would help.

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

  Parameters3/5

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

  The schema description coverage is 0%, but the description adds value by listing example button names (BACK, HOME, RECENT, ENTER) in the Args section. However, it doesn't fully compensate for the lack of schema details, such as whether other buttons are allowed or the format constraints.

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

  Purpose4/5

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

  The description clearly states the action ('Press') and target ('physical or virtual button on the Android device'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like 'mobile_click' or 'mobile_type', which might involve similar interactions.

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives like 'mobile_click' or 'mobile_type'. The description implies button-pressing scenarios but lacks explicit context or exclusions, leaving usage unclear relative to siblings.

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

• mobile_swipeC
  2.9/5.0
  Behavior2/5

  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 without disclosing behavioral traits. It doesn't mention potential side effects (e.g., screen changes, app navigation), error conditions, or dependencies like requiring an active Android session, which is critical 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.

  Conciseness4/5

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

  The description is front-loaded with the core purpose in the first sentence, followed by a structured Args section. It's efficient with minimal waste, though the parameter explanations could be slightly more informative without sacrificing brevity.

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

  Completeness3/5

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

  Given 5 parameters with 0% schema coverage and no annotations, the description provides basic parameter info but lacks behavioral context. The presence of an output schema (not detailed here) might help, but for a mutation tool in a mobile automation context, more guidance on effects and prerequisites is needed for full completeness.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate. It lists all 5 parameters with brief explanations (e.g., 'Starting X coordinate'), adding basic meaning beyond the bare schema. However, it lacks details like coordinate ranges (e.g., screen resolution limits) or units, leaving gaps in understanding.

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

  Purpose4/5

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

  The description clearly states the action ('perform a swipe gesture') and target ('on the Android screen'), which is specific and distinguishes it from siblings like mobile_click or mobile_type. However, it doesn't explicitly differentiate from mobile_dump_ui or mobile_take_screenshot in terms of interaction type, keeping it from 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.

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives like mobile_click for taps or mobile_key_press for keyboard inputs. The description lacks context about prerequisites (e.g., needing mobile_init first) or typical use cases, leaving the agent to infer usage.

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

• mobile_launch_appB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Launch') but lacks details on permissions needed, whether the app must be installed, error handling (e.g., if package_name is invalid), or system requirements. This is a significant gap 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.

  Conciseness4/5

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

  The description is appropriately sized and front-loaded, with the core purpose stated first and parameter details in a separate section. It avoids unnecessary words, though the structure could be slightly more integrated (e.g., merging the Args section into the main text).

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

  Completeness3/5

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

  Given the tool's moderate complexity (a mutation with one parameter) and the presence of an output schema (which reduces the need to describe return values), the description is minimally adequate. However, it lacks behavioral details and usage guidelines, making it incomplete for safe and effective use.

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

  Parameters4/5

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

  The description adds meaningful context beyond the input schema, which has 0% coverage. It explains that package_name identifies the app to launch and provides an example ('com.android.chrome'), clarifying the parameter's purpose and format, though it doesn't cover all possible edge cases.

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

  Purpose4/5

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

  The description clearly states the tool's purpose with a specific verb ('Launch') and resource ('application by its package name'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like mobile_init or mobile_list_apps, which prevents 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.

  Usage Guidelines2/5

  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 (e.g., whether mobile_init must be called first), exclusions, or comparisons to siblings like mobile_click or mobile_list_apps, leaving usage context unclear.

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

• mobile_take_screenshotA
  3.7/5.0
  Behavior2/5

  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. It mentions the return type ('image object') but lacks critical details: whether this requires specific permissions, if it works on locked screens, potential latency, or error conditions. The description adds some value but leaves significant behavioral gaps.

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

  Conciseness5/5

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

  Two concise sentences with zero waste: first states the core action, second clarifies the return value. Perfectly front-loaded with essential information, no redundant phrasing or structural issues.

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

  Completeness3/5

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

  Given the tool's moderate complexity (device interaction with no parameters but no output schema), the description is minimally adequate. It covers purpose and return type but lacks behavioral context (permissions, constraints) that would be expected for a device control tool without annotations. The absence of an output schema means the description should ideally detail the image format or viewing method, which it only partially addresses.

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

  Parameters4/5

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

  The tool has 0 parameters with 100% schema description coverage (empty schema). The description appropriately doesn't discuss parameters since none exist, which aligns with the baseline expectation for parameterless tools. No additional parameter context is needed or provided.

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

  Purpose5/5

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

  The description clearly states the specific action ('Take a screenshot') and target resource ('current Android screen'), distinguishing it from sibling tools like mobile_dump_ui (which likely provides UI hierarchy data) or mobile_click (which performs interaction). It uses precise verb+resource phrasing without being tautological.

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

  Usage Guidelines3/5

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

  The description implies usage context (when you need a visual capture of the Android screen) but doesn't explicitly state when to use this versus alternatives like mobile_dump_ui for structural UI data. No guidance on prerequisites (e.g., device must be unlocked) or exclusions is provided.

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

• mobile_list_appsA
  3.8/5.0
  Behavior2/5

  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 it returns a JSON array. It doesn't disclose behavioral traits like whether this requires device permissions, if it's read-only/safe (implied but not explicit), rate limits, or error conditions. The description adds minimal value 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.

  Conciseness5/5

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

  Two sentences with zero waste: first states purpose, second specifies return format. It's front-loaded with the core action and efficiently structured, with every sentence earning its place by adding distinct value.

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

  Completeness4/5

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

  Given the tool's low complexity (0 params, output schema exists), the description is reasonably complete. It covers what the tool does and return format, though lacks behavioral context like permissions or errors. With an output schema handling return values, the description doesn't need to detail JSON structure further.

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

  Parameters4/5

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

  The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents inputs. The description appropriately doesn't add parameter details, maintaining focus on the tool's purpose. Baseline 4 is correct for zero-parameter tools.

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

  Purpose5/5

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

  The description clearly states the specific action ('List all installed applications') and resource ('on the Android device'), distinguishing it from siblings like mobile_launch_app (which launches apps) and mobile_dump_ui (which dumps UI). It precisely defines scope without ambiguity.

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

  Usage Guidelines3/5

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

  The description implies usage context (Android device management) but provides no explicit guidance on when to use this tool versus alternatives. It doesn't mention prerequisites like needing mobile_init first or compare with other list/query tools, leaving usage decisions to inference.

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

• mobile_dump_uiA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the output format and filtering criteria ('Only includes focusable elements or elements with text/content_desc/hint attributes'), which adds useful context beyond basic functionality. However, it lacks details on performance, error handling, or dependencies (e.g., requiring an active Android session).

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

  Conciseness5/5

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

  The description is front-loaded with the core purpose in the first sentence, followed by clarifying details in subsequent sentences. Each sentence adds value: the first defines the action and output, the second explains the hierarchical structure, and the third specifies inclusion criteria. There is no wasted text.

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

  Completeness4/5

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

  Given the tool's complexity (UI element extraction), no annotations, and an output schema present, the description is reasonably complete. It covers the purpose, output format, and filtering logic. However, it could benefit from mentioning prerequisites (e.g., device connectivity) or limitations (e.g., screen state requirements), slightly reducing completeness.

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

  Parameters4/5

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

  There are 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description does not discuss parameters, which is appropriate here. A baseline of 4 is applied as it efficiently handles the lack of parameters without redundancy.

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

  Purpose5/5

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

  The description clearly states the tool's purpose with specific verb ('Get UI elements') and resource ('from Android screen'), and distinguishes it from siblings by focusing on UI element extraction rather than interaction (e.g., mobile_click) or system actions (e.g., mobile_launch_app). It specifies the output format ('as JSON with hierarchical structure'), which is unique among the listed tools.

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

  Usage Guidelines3/5

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

  The description implies usage for retrieving UI elements in a structured format, but does not explicitly state when to use this tool versus alternatives like mobile_take_screenshot for visual capture or mobile_list_apps for app enumeration. No exclusions or prerequisites are mentioned, leaving usage context somewhat open-ended.

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

• mobile_typeA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses the basic behavior (text input with optional submission) but lacks details like error conditions (e.g., if no field is focused), performance characteristics, or platform-specific constraints. It adequately covers the core operation but misses advanced context.

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

  Conciseness5/5

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

  The description is front-loaded with the core purpose, followed by a structured Args section. Every sentence earns its place—no fluff or repetition. It's efficiently sized for the tool's complexity.

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

  Completeness4/5

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

  Given the tool's moderate complexity (2 parameters, no annotations, but with an output schema), the description is mostly complete. It covers purpose and parameters well, but lacks behavioral nuances like error handling. The output schema likely handles return values, so that gap is acceptable.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It clearly explains both parameters: 'text' as the content to input and 'submit' as triggering an Enter key press. This adds essential meaning beyond the bare schema, though it doesn't detail format constraints or examples.

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

  Purpose5/5

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

  The description clearly states the specific action ('Input text') and target resource ('currently focused text field on Android'), distinguishing it from sibling tools like mobile_click or mobile_key_press. It precisely defines the tool's scope without ambiguity.

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

  Usage Guidelines3/5

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

  The description implies usage when text input is needed on Android, but provides no explicit guidance on when to use this versus alternatives like mobile_key_press for individual keystrokes or mobile_click to focus fields first. 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.

• mobile_initA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that this is a setup/initialization tool with a prerequisite role, which is useful behavioral context. However, it doesn't mention potential side effects (e.g., establishing a session, requiring device availability), error conditions, or what 'initialize' entails operationally. For a tool with no annotations, this leaves gaps in behavioral understanding.

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

  Conciseness5/5

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

  The description is highly concise and well-structured: two sentences with zero waste. The first sentence states the purpose, and the second provides critical usage guidance. Every word earns its place, making it easy to parse and front-loaded with essential information.

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

  Completeness4/5

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

  Given the tool's low complexity (0 parameters, initialization role) and the presence of an output schema (which handles return values), the description is reasonably complete. It covers purpose and prerequisites adequately. However, for a tool with no annotations, it could benefit from more behavioral details (e.g., what happens on failure, session management), slightly reducing completeness.

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

  Parameters4/5

  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 the baseline is 4. The description adds no parameter information, which is appropriate since there are no parameters. It implicitly confirms the lack of parameters by not mentioning any, aligning with the schema.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: 'Initialize the Android device connection' specifies the verb (initialize) and resource (Android device connection). It distinguishes from siblings by being a prerequisite setup tool rather than an action tool like mobile_click or mobile_launch_app. However, it doesn't explicitly differentiate from potential other initialization tools (none in siblings), so it's not a perfect 5.

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

  Usage Guidelines5/5

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

  The description provides explicit usage guidelines: 'Must be called before using any other mobile tools' clearly states when to use this tool (as a prerequisite) and when not to use it (after initialization or for other purposes). It implies alternatives by indicating this is required for all sibling tools, making usage context unambiguous.

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