notification_bar_clear

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

Since no annotations are provided, the description fully carries the burden of behavioral disclosure. It details the tap location (50,850), the backend order (idb else Maestro), the screenshot comparison method, and explicitly notes the heuristic nature and potential unreliability. This is thorough and honest about limitations.

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, with three sentences covering purpose, mechanism, and caveats. It is front-loaded with the primary action and structured logically. While every sentence earns its place, the note about the heuristic slightly extends the length; however, it is necessary for transparency.

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 low complexity and absence of an output schema, the description provides adequate context. It explains the tool's goal, method, and limitations (heuristic, device-specific). No return value is described, but that is acceptable without an output schema. The description could include a note about potential side effects (e.g., accidental taps), but overall it is 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?

The input schema already describes both parameters with 100% coverage. The description adds value by explaining that 'bundleId' is only used for the Maestro fallback and can be auto-detected, which provides context beyond the schema's 'App bundle id for the Maestro fallback' description. For 'udid', no additional meaning is added, but the overall contribution justifies above baseline 3.

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

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

The description clearly states the tool's purpose: to dismiss the React Native debug notification bar. It specifies the action ('dismiss'), the target resource ('debug notification bar'), and the context ('appears at the bottom of the screen and intercepts taps'). This distinguishes it from sibling tools like tap_on or tap_with_fallback, which are generic tap actions.

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 the tool (when the debug notification bar appears), but it does not provide explicit guidance on when not to use it or suggest alternatives. For example, it does not mention that other tools should be used for non-debug bars or general interactions. The context is clear but lacks comparative direction.

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