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

Annotations indicate destructiveHint=true (mutates state) and readOnlyHint=false, but the description adds no behavioral context beyond what annotations already convey. It does not explain side effects, permissions needed, or that operations like 'clear-data' are destructive.

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?

At three words, the description is under-specified, not concise. For a tool with 6 parameters and multiple operations, it should provide structured detail without wasting words. Current form fails to inform.

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

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

Given the tool's complexity (6 parameters, no output schema, multiple operations), the description is inadequate. It does not explain return values, pagination behavior, or how operations like 'list' work. The agent has to infer everything from parameter names and enum values.

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

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

Schema description coverage is 67%, with some parameters (apkPath, limit, filter) having descriptions. The description 'Manage applications' does not add meaning beyond the schema. However, the moderate coverage means the schema partially compensates, so a 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?

The description 'Manage applications' is vague and does not specify the supported operations (install, uninstall, launch, etc.). The input schema lists operations but the description fails to enumerate them, making it unclear what this tool specifically does compared to siblings.

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 siblings like adb-device or adb-logcat. The description offers no context for selecting this tool for app management tasks.

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 are all false, but the description adds no behavioral context. There is no mention of side effects, read-only nature, or any other behavioral traits beyond the tool name.

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 short but achieves conciseness at the cost of clarity. While there is no wasted text, it is under-specified.

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 has 2 parameters, no output schema, and minimal annotations, the description is insufficient. It does not explain the operations or how to use the deviceId parameter.

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

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

Schema description coverage is 0%. The description does not explain the 'operation' or 'deviceId' parameters. The enum for operation is implicit but not described, and deviceId is completely undefined.

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 'Manage device connections' is vague and does not differentiate from siblings like adb-app or adb-shell. The operation enum in the schema provides some clarity, but the description itself lacks specificity.

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 such as adb-app or adb-logcat. The description does not indicate prerequisites or context for usage.

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 readOnly and idempotent, so the description adds minimal value. It does not explain what 'summary' means or any behavioral traits beyond reading logs.

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 and efficient, but it sacrifices necessary detail. It is front-loaded but incomplete.

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 6 parameters and no output schema, the description is severely lacking. It does not explain how to filter logs, what the logId represents, or the return format.

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 description adds no meaning to the 6 parameters, especially the 4 undocumented ones (package, tags, level, rawFilter). Schema coverage is only 33%, and the description fails to compensate.

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 reads device logs, which is a specific verb+resource. However, it does not differentiate from siblings like adb-device or adb-shell, leaving ambiguity about the log source.

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. It lacks information about prerequisites, context, 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?

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds 'with safety guards', hinting at restrictions, but does not specify what those guards are (e.g., command whitelisting, output limits). Adds marginal context beyond 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 concise (single phrase) and front-loaded with the verb. However, it might be too terse for a tool that requires careful usage.

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

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

Given 5 parameters, no output schema, and destructive behavior, the description is insufficient. It lacks examples, return format, and details on safety guards. More information is needed for appropriate agent 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?

Schema coverage is 80% with descriptions for most parameters except 'command'. The description does not add meaning for the undocumented 'command' parameter, which is required. It simply restates the tool's purpose without clarifying acceptable values or formats.

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 (execute) and resource (shell commands), and adds a hint about safety guards. It is distinct from sibling tools like adb-logcat or adb-app, though it could be more specific about the context (Android ADB).

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. With siblings like adb-logcat and adb-app, there is no indication of selection criteria or when not to use the 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?

Annotations indicate destructiveHint=true and readOnlyHint=false, consistent with cache management. However, the description adds no behavioral context beyond annotations, such as what data is affected, auth requirements, 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 very short (two sentences) but overly terse. It sacrifices completeness for brevity, and the reference to external docs reduces self-contained value. Not front-loaded with critical info.

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 has multiple operations, a nested config object, and no output schema, the description is severely incomplete. It fails to explain what each operation does, how parameters behave, or what results are 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 description coverage is only 33% (only 'key' has a description). The description provides no parameter details, failing to compensate for the low coverage. The enum for 'operation' is documented only 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?

The description says 'Manage the cache' which is a tautology of the tool name and lacks specificity. It does not list the available operations or differentiate from sibling tools, though no sibling directly manages cache. The reference to 'rtfm' suggests external documentation is needed.

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. The description instructs to 'See rtfm for details' but provides no context on appropriate usage vs alternatives. 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 indicate destructiveHint: true and readOnlyHint: false, which is helpful, but the description adds no context about side effects, required permissions, or which operations are destructive. The description does not elaborate beyond what annotations already provide.

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 but at the cost of under-specification. Every sentence should earn its place; here, the single sentence is too vague to be useful.

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 no output schema and sparse annotations, the description fails to cover essential context such as return values, error conditions, or prerequisites for the various operations. It is inadequate for a multi-operation tool.

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

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

Schema description coverage is only 17%, with only one parameter ('device') having a brief example. The description does not explain the meaning or format of any other parameters (avdName, systemImage, snapshotName, emulatorId), leaving the agent to guess.

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

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

The description states 'Manage Android emulators,' which identifies the resource but uses a vague verb. It is not specific to any single operation, and does not distinguish from sibling tools like adb-device.

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, nor any exclusions or prerequisites for specific operations. The agent receives no help in deciding 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 indicate readOnlyHint=false and destructiveHint=false, but the description adds no behavioral context beyond 'Build'. No mention of side effects, required project state, or failure behavior.

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

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

The description is very short (one sentence) but under-specified. It is not appropriately sized for a tool with three parameters and no output schema.

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?

Description is severely incomplete. It does not explain the build process, return value (beyond having a buildId), or relationship to sibling tools. No output schema exists to compensate.

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 33% (only module described). The description does not explain any parameters, including the required 'operation' enum or the optional 'flavor'. Agent gets no help understanding parameter meaning.

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 says 'Build' which is almost a tautology with the tool name 'gradle-build'. It does not specify what kind of build (e.g., Android app) or distinguish from sibling tools like gradle-test.

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 siblings like gradle-get-details, gradle-list, or gradle-test. No context about prerequisites or scenarios.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, covering key behavioral traits. The description adds 'full output' but doesn't elaborate on truncation via maxChars or summaryOnly options, or on rate limits.

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 8-word sentence is very concise and front-loaded. However, it omits useful details that could be included without exceeding reasonable length.

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 (5 parameters, no output schema), the description does not explain return values or how to interpret output. It lacks details on how summaryOnly, maxChars, and previewChars affect behavior, making it incomplete for effective use.

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

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

With 60% schema coverage, 2 parameters (id, detailType) lack schema descriptions. The description does not mention any parameters or their meaning, failing to compensate for missing schema explanations.

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 the tool fetches full output for a previous build/test by ID, using 'Fetch' as the verb and 'full output' as the resource. It distinguishes from sibling tools like gradle-build (creates builds) and gradle-list (lists builds), but does not explicitly differentiate.

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., gradle-list, gradle-test). The description implies you need an ID but doesn't specify prerequisites or scenarios where other tools are 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the description does not need to repeat these. The description adds no further behavioral context, such as side effects or authentication needs, but given the annotations, a score of 3 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 a single sentence, extremely concise. It front-loads the purpose but lacks any detail about parameters or usage. For a tool with a simple enum-based parameter set, this brevity is acceptable but could benefit from a bit more 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 tool's simplicity and the presence of annotations, the description is mostly complete. However, without an output schema, the agent might need to know what the tool returns. The description does not hint at the output format, leaving a slight gap in 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 2 parameters with 50% description coverage: 'module' has a description 'e.g., ':app'', but 'operation' only has an enum. The tool description does not add any parameter meaning beyond the schema. Since the schema provides sufficient detail for the enum, a baseline of 3 is 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 'Introspect project structure' combined with the tool name 'gradle-list' clearly indicates that this tool lists elements of the project structure. However, it does not specify that it can list variants, modules, or tasks, which is covered by the input schema enum. The verb 'introspect' is less common but still conveys inspection.

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 siblings like gradle-build or gradle-get-details. It does not mention exclusions or context of use, leaving the agent to infer from the name and schema alone.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds the context of auto-detecting regressions with baseline, which provides additional behavioral insight beyond the annotations. However, it does not elaborate on side effects or destruction scope. No contradiction with annotations is present.

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 and front-loaded with the core action. It is efficient, though the phrase 'With baseline, auto-detects regressions' could potentially be integrated more succinctly. Still, it is notably concise and to the point.

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

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

There is no output schema, so the description should explain the return value in more detail. It only states 'Returns summary with testId,' leaving ambiguity about the summary content. Additionally, the description does not elaborate on when baseline is used or how regressions are detected, leaving gaps given the tool's complexity (4 parameters, destructive nature).

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 50% description coverage, with descriptions for 'filter' and 'taskName'. The description adds no parameter-specific details beyond the schema. Baseline score is 3 given the moderate schema coverage, and the description does not compensate further.

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 'Run tests' as the primary action, explicitly mentions returning a summary with testId, and introduces baseline regression detection. This distinguishes it from sibling tools like gradle-build, gradle-get-details, or gradle-list, all of which have different purposes.

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 running tests and mentions baseline regression detection, but it does not explicitly state when to use this tool versus alternatives, nor does it provide when-not-to-use guidance. Some context is given, but it lacks explicit exclusions or alternatives.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, making safety clear. Description adds minimal behavioral info beyond the query options, so score is average.

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 wasted words, easy to parse.

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

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

Explains input options well but lacks detail on output format; however, for a documentation tool this is acceptable given complexity is low.

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 has 100% description coverage; description adds example values but does not significantly expand meaning beyond schema defaults.

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 retrieves documentation, listing specific categories and tool names, differentiating it from sibling tools that are actual operations.

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 instructions on passing either category or tool, but does not explicitly state when not to use this tool versus alternatives; context is clear enough though.

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 and readOnlyHint=false. The description adds the 'tap, input, scroll' actions, which align with mutability. However, it does not disclose other behavioral traits like side effects, auth needs, or error conditions beyond what annotations provide.

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: a single sentence with no redundancy. It front-loads the core functionality ('Interact with app UI: tap, input, scroll') and adds a key usage hint ('Use selector or coords').

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?

Despite 9 parameters, nested objects, and no output schema, the description is very brief. It lacks details on parameter combinations, defaults, error handling, return values, and behavioral context. The tool is complex, and the description is not sufficiently complete.

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?

With only 22% schema description coverage, the description should compensate but does not. It lists operations but provides no additional meaning for most parameters (e.g., selector, elementIndex, x/y) beyond the schema. Two parameters (amount, deviceSpace) have descriptions, but that is minimal compensation.

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: interacting with app UI via tap, input, and scroll actions. It uses specific verbs and resource reference, and the list of operations distinguishes it from sibling tools like ui-capture and ui-query.

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 UI interactions but provides no explicit when-to-use or when-not-to-use guidelines, nor does it mention alternatives or prerequisites. The context is implied but not detailed.

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 readOnlyHint=false, suggesting side effects, but the description simply says 'capture', implying a read operation without disclosing any behavioral traits such as file creation, state changes, or output format. The description contradicts annotations, failing to clarify 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 extremely concise (one sentence), but it omits critical details. While brevity is valued, it sacrifices necessary information, resulting in under-specification rather than optimal 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 tool has 5 parameters (1 required), no output schema, and no behavioral transparency, the description is insufficient. It fails to explain the tool's purpose in context of its complexity and does not cover return values or usage nuances.

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?

With only 40% schema description coverage, the description adds no clarification for parameters like 'operation', 'localPath', or 'inline'. It does not explain the difference between the two operation enum values, leaving the agent without essential semantic 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 verb 'capture' and resource 'screenshots or visual snapshots', distinguishing it from sibling tools like 'ui-action' and 'ui-query' which focus on interaction and querying. However, it lacks precision on what 'visual snapshots' entails beyond screenshots.

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, scenarios, or contrasts with siblings, leaving the agent to infer usage from the tool name alone.

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

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

Annotations already declare read-only, non-destructive, and idempotent behavior. The description adds 'accessibility-first' hinting at a focus on accessibility properties, which is modest additional context beyond 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?

At only 4 words, it is too brief for a complex tool with multiple operations and parameters. Front-loading purpose is good, but the lack of structure and detail harms usability.

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 9 parameters, 3 operations, nested objects, and no output schema, the description is severely incomplete. It omits critical information about selector syntax, tier meaning, grid parameters, return format, and operation semantics.

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 9 parameters but only 33% coverage with descriptions. The tool description does not explain any parameters or operations (e.g., what 'dump', 'find', 'accessibility-check' do), failing to compensate for low 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 'Query app UI.' states the general purpose but lacks specificity about the available operations (dump, find, accessibility-check) and does not distinguish from sibling tools like ui-action or ui-capture.

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. Sibling tools (e.g., ui-action, ui-capture) exist but the description provides no criteria for selection or exclusion.

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