ui_screenshot

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

There are no annotations, so the description carries the full burden, yet it says nothing about required device state (unlocked, app running), failure modes, permissions, or what the call returns beyond the file. For a tool that has a sibling device_unlock, the missing precondition about screen state is a notable gap.

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?

One short sentence with the action and location front-loaded and zero filler; the parenthetical adds a use hint rather than padding.

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 no annotations and no output schema, the agent gets the deliverable but not the prerequisites: whether the device must be connected/unlocked, what happens if the screen is off, or the return value. Adequate but clearly short of complete for a device-dependent tool.

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 100% and the single parameter's description ('Where to save it; default under the downloads dir') already explains the default. The description adds only the 'on this computer' framing, so baseline 3 is appropriate.

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 names a concrete verb (save) and resource (PNG screenshot of the phone screen) plus a location, so the agent knows exactly what the call produces. It implicitly distinguishes itself from UI-interaction siblings like ui_tap or ui_scroll, though no sibling is named explicitly.

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 parenthetical 'look at it to see the UI' implies the intended use—visual inspection of the current screen—but it never states when to prefer this over ui_dump or ui_find for examining the UI, nor any preconditions.

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