screenshot

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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly communicates that the tool captures the current screen and returns a PNG, and explains the model's visual access to the screen. It does not discuss side effects or permissions, but screenshot is inherently a read-only operation and the description is sufficiently transparent for this tool.

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 compact and front-loaded, with the first sentence stating the operation and output format and the second adding relevant use-case context. Every sentence earns its place and there is no redundant 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?

For a simple, side-effect-free tool, the description covers the action, the output format, and the main use case. The only notable gap is the undocumented serial parameter, which is optional, so the description is still mostly complete but not fully self-sufficient for multi-device scenarios.

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 input schema has one parameter, serial, with 0% schema description coverage, and the description does not mention serial at all. This leaves the agent without any explanation of whether serial selects a specific device, what values are valid, or what happens when it is null. The description fails to compensate for the schema's lack of parameter documentation.

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 states a specific action and result: taking a screenshot of the device and returning it as a PNG image. It also explicitly contrasts itself with ui_dump, giving a clear purpose distinction from a key sibling tool.

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: when ui_dump is insufficient for visually rendered content such as games, video, custom-drawn UI, or WebView/Canvas. It does not explicitly state when not to use it or mention alternatives like screen_record or ocr_screen, so it narrowly misses a 5.

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