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

With no annotations provided, the description carries the full burden. It discloses the polling/blocking behavior ('poll until... or timeout'), default timeout via schema, and the physical-pixel coordinate return format. This is meaningful behavioral context beyond the schema, though it doesn't state failure behavior on timeout or whether it throws an error.

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 are front-loaded with the core behavior. Every clause adds value — the physical-pixel detail is a useful hook to device_tap. Could arguably be a 5, but it could have mentioned default values or failure semantics in passing; still very efficient.

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

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

For a 5-param polling utility with no output schema and no annotations, the description explains the mechanism (poll, timeout), the return format (physical coordinates), and the primary consumer (device_tap). It's slightly light on timeout failure behavior and doesn't hint at output schema, but the core usage loop is fully described.

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 well-described params (text, resourceId, udid, timeout, interval all have descriptions). The description adds the key semantic that text accepts 'visible text or content-desc' and that coordinates are in physical pixels, which enriches value. Baseline 3 applies since schema already does the heavy lifting; description adds modest 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?

Description states a specific verb+resource: 'Poll the UI until an element with the given text or resource-id appears, or timeout.' It clearly distinguishes from siblings like device_find_element (which snapshots) and device_tap (which acts on found coordinates), and ties directly to device_tap output format.

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 'until X appears, or timeout' describes the polling/waiting behavior clearly, and the note that it returns coordinates 'ready for device_tap' establishes a clear downstream usage pattern. However, it doesn't explicitly state when-not to use it vs. device_find_element, device_elements_in_region, or device_scroll_to_element, which are close siblings.

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