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

The description goes well beyond the sparse annotations by explaining timeout semantics (explicit error, never false success), the return payload shape, and the subtle enabled_unknown edge case with AXEnabled. This is rich behavioral disclosure that is genuinely useful for an agent deciding whether the call succeeded as intended.

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?

Three dense sentences, each earning its place. The most important claim ('replaces all sleeps') is front-loaded, and the subtle enabled_unknown caveat is included without bloat. The structure is clear and scannable.

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?

The description covers core behavior, timeout semantics, and return values unusually well, but it leaves element selection ambiguous: with zero required parameters, it is unclear whether role/label are needed, or what happens when none are supplied. The role/label/match/window_id/app_bundle_id semantics are a notable gap for a tool with this many parameters and no output schema to clarify results.

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 only 38%, and the description adds real meaning for state and timeout behavior but does little for role, label, match, window_id, or app_bundle_id. The state:'enabled' nuance and timeout-as-error detail compensate partially, but several element-locator parameters remain unexplained beyond their names.

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 opens with a specific purpose — deterministic synchronization that replaces sleeps — and clearly states the polling behavior and state targets (present|enabled|focused|absent). This clearly differentiates it from sibling tools like ui_find_element and ui_get_element by emphasizing waiting for a state over time, not mere lookup.

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?

It explicitly frames the tool as the replacement for sleeps, giving strong context for when to use it: whenever deterministic waiting for a UI state is needed. It does not explicitly name alternatives like ui_find_element or state when *not* to use it, but the 'replaces all sleeps' guidance is clear and actionable.

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