get_screen

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

With no annotations provided, the description carries the full transparency burden. It clearly indicates that the operation is a read of the current screen and explains the output format. It does not disclose edge-case behaviors such as errors when the screen is off or the device is disconnected, but for a simple read tool the core behavior is well communicated.

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?

The description is two short sentences with no filler. The core action and output format are front-loaded, and the usage guidance follows naturally. Every sentence earns its place.

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?

Given the tool's low complexity scrap output schema exists and the description covers what it does, what it returns, and when to call it, the main remaining gap is the undocumented device parameter. That is a modest omission rather than a fundamental completeness failure.

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?

The schema has one parameter, device, with 0% description coverageane the description never mentions it. The tool description does not add any meaning about how to specify or omit the device parameter. The optional nature and default value in the schema reduce the risk, but the description still fails to compensate for the missing parameter guidance.

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 uses a specific verb ('Read') and a clear resource ('what is currently on the phone screen'), and further specifies the output as a 'numbered list of tappable elements.' This also distinguishes it from siblings like take_screenshot, which would return a visual image rather than structured tappable elements.

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 description gives clear context for when to use the tool: 'call it before acting, and after anything unexpected.' It also positions itself as 'the main way to see the phone.' However, it does not explicitly name alternatives or state when not to use it, so it stops short of a 5.

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