Send input

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

With no annotations, the description carries the full burden. It does disclose the action vocabulary and valid key values (BACK, HOME, ENTER, APP_SWITCH, DEL, any KEYCODE_*), which is real behavioral context. But it says nothing about what happens on failure, whether the call blocks until the UI settles, timing/rate considerations, or what a successful call returns (there is no output schema).

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?

Two sentences, zero filler. The capability statement comes first and the follow-up hint (ui_dump for coordinates) is a single useful clause rather than a paragraph.

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 9-parameter, mutation-style device-control tool with no annotations and no output schema, the description covers the action surface well. The remaining gap is outcome reporting and device-selection behavior, though the latter is partly documented in the serial parameter of the schema.

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 67% and the description fills some of the gap: it maps actions to the coordinate/text/key parameters and enumerates the accepted key names, which the schema only gestures at with 'Key name or keycode'. It still leaves the x/y vs x2/y2 start-end relationship for swipes implicit, relying on the schema's 'Swipe end x/y' notes.

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?

States a specific verb and resource ('Drive the device UI') and enumerates exactly what it can do: tap or long-press at coordinates, swipe, type text, press a key. An agent can distinguish it from sibling tools like adb_shell, screenshot, or ui_dump without opening the schema, and the final sentence points at ui_dump as the source of coordinates.

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?

Gives an actionable usage pointer — 'Get coordinates from ui_dump' — which establishes the intended workflow pairing. It does not, however, state when to prefer this over adb_shell for input injection, nor any prerequisite like a connected/online device or which device gets targeted when several are online.

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