Wait For Screen Change

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

With no annotations, the description carries the full burden, and it discloses almost nothing: what happens on timeout (error, null, or stale return), whether it captures a baseline snapshot first, and how polling interacts with the wait are all unstated. 'Differs from now' is the only behavioral hint, implying a comparison against a captured initial state.

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?

A single short, front-loaded sentence with no wasted words, but its brevity is under-specification rather than efficiency given the tool's 3-parameter surface and many siblings.

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?

An output schema exists so return values needn't be spelled out, but the absence of annotations and any parameter or timeout-behavior explanation leaves the definition incomplete for a tool whose semantics hinge on polling and timeout.

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% across three parameters. The description never mentions poll, timeout, or device, so nothing compensates for the undocumented schema — an agent cannot know what units 'poll'/'timeout' use or what 'device' selects.

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 verb 'wait' plus the resource 'screen change' make the core action understandable, and 'differs from now' clarifies that it blocks on a UI delta. However, it never distinguishes itself from the many sibling wait tools (wait_for, wait_for_idle, wait_for_text, wait_for_nodes), so an agent cannot tell which waiter to pick from the text alone.

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?

There is no when-to-use guidance, no conditions, and no named alternative. Given the crowded sibling set of wait_* and perceive/read_screen tools, the description leaves the routing decision entirely to the agent.

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