Touchpoint

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

Reveals the polling mechanism ('Polls the application list'), which is valuable behavioral context. However, with no annotations provided, it fails to disclose critical behavioral details like failure mode when timeout is reached, polling frequency, or the blocking nature of the operation.

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?

Well-structured with purpose front-loaded, followed by implementation details, usage context, and parameter documentation. The Args section format is slightly informal but efficiently conveys necessary semantics without redundancy.

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?

Appropriately complete for a 3-parameter tool with an output schema present; parameter documentation compensates for poor schema coverage. Minor gap regarding timeout failure behavior, but sufficient for agent selection and invocation.

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?

With 0% schema description coverage, the description fully compensates by documenting all three parameters in the Args section: 'app' includes concrete examples ('Firefox', 'Slack'), 'timeout' clarifies units and default value, and 'gone' clearly explains the boolean inversion logic.

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 specific action ('Wait') and resource ('application') with precise conditions ('appear or disappear'), effectively distinguishing it from similar siblings like wait_for_window and generic wait_for.

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?

Provides explicit temporal guidance ('Use after launching or closing an application'), but lacks explicit differentiation from siblings like wait_for_window or wait_for_element, leaving some ambiguity about when to choose this specific wait variant.

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