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

With no annotations, the description carries the full burden of behavioral disclosure. It usefully reveals that the tool polls, can time out, and returns physical-pixel coordinates ready for tapping. However, it does not clarify what happens on timeout (error vs. null), how text/content-desc matching works, or behavior when both text and resourceId are supplied.

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 entire description is one tight, front-loaded sentence. It states the action, the condition, the termination behavior, and the output format without wasted words. The emphasis on PHYSICAL pixels is a valuable, concise detail.

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 there is no output schema and no annotations, the description covers the main behavior but leaves important operational details unspecified, such as timeout failure behavior and the exact structure of the returned coordinates. It is adequate for a simple polling tool but not fully complete for an agent that must handle failure cases.

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%, so the parameters are already documented. The description adds value by grouping 'text or resource-id' as alternative matching criteria and noting that output coordinates are in physical pixels, but it does not provide additional per-parameter semantics 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 function with a specific verb ('poll'), resource ('UI'), condition ('until an element with the given text or resource-id appears'), and termination behavior ('or timeout'). It also distinguishes itself from immediate-lookup siblings like device_find_element by emphasizing polling and yielding coordinates for device_tap.

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: wait for a UI element to appear, then use the returned coordinates with device_tap. However, it does not explicitly state when to prefer this over alternatives such as device_find_element or ios_wait_for_element, nor does it mention any exclusions or preconditions.

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