Wait For

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

No annotations are provided, so the description carries the full burden, and it does well: it discloses that the condition is echoed back and that the agent must judge the returned state, and it documents timeout defaults/limits (5000ms default, 30000ms max) and polling behavior (500ms default, 100ms min). It omits failure semantics—what the return looks like when a timeout expires.

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?

Front-loads the scoping rule and then the condition semantics, then timeouts—a sensible order. The middle sentence is long and packs several clauses, but each sentence contributes information rather than filler.

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 an output schema present, the description needn't explain return values, and it covers the condition model, mutual exclusion of text/package/activity, and timing controls adequately for a 10-param tool. The main remaining gap is the undocumented device parameter and timeout-failure behavior.

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 0% across 10 parameters, so the description must compensate, and it explains the semantics of text/package/activity (wait until on screen), gone (invert to until-disappears), timeout_ms/poll_interval_ms defaults and bounds, and the timeout/interval seconds aliases. It leaves device and condition's accepted formats underspecified, so it is strong but not complete.

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?

States a specific verb+resource: wait until a condition holds, with concrete condition categories (downloads, uploads, processing, status changes). It distinguishes itself from gesture tools by declaring gestures already settle, but does not explicitly differentiate from near-siblings like wait_for_text, wait_for_idle, or wait_for_screen_change.

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?

Gives a clear when-to-use constraint ('LONG waits only') and a when-not-to-use rule ('gestures already settle'), plus branch conditions for text/package/activity vs. generic loading. It stops short of naming the sibling tools that cover the excluded quick-settle cases.

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