Waits up to 20 seconds for a UI selector to appear or meet conditions; returns found=false on timeout so callers can distinguish missing elements from business failures.
Wait at most 20 seconds for a selector. found=false means timeout, not business failure.
| Name | Required | Description | Default |
|---|---|---|---|
| selector | Yes | ||
| timeout_seconds | No |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is covered; the description adds real value by clarifying that 'found=false means timeout, not business failure' — a semantic distinction an agent would otherwise misread as an error. The 20-second ceiling is repeated from the schema's maximum, which is mildly redundant but harmless.
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 tight sentences with no filler; the action and its bound come first, followed by the critical interpretation note about the return flag. Nothing could be removed without losing 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?
With no output schema, the description carries the burden of describing the return value, and it explains only the 'found' flag while leaving the rest of the response shape unstated. For a tool whose selector is a large undocumented nested object, more guidance on matching behavior is needed, though the timeout semantics are adequately covered.
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% and the selector is an 11-field nested object (text, index, enabled, focused, package, clickable, class_name, description, resource_id, text_contains, description_contains) with no explanation anywhere of matching semantics or whether fields combine as AND. The description only restates the timeout ceiling already encoded as the schema maximum, adding essentially nothing about parameters.
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?
Specific verb (wait) plus resource (selector) and a hard bound (20 seconds), so an agent immediately knows this is a blocking conditional wait rather than an instantaneous lookup. It does not explicitly name the sibling it replaces (aua_find for immediate checks, aua_pause for fixed delays), so differentiation is inferable rather than stated.
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 20-second cap and 'found=false' phrasing imply this should be used when an agent needs to block on an element appearing, which hints at the when-to-use case. However, there is no explicit guidance versus aua_find or aua_pause, and no statement of what happens after a timeout in terms of next steps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.