act

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

With no annotations, the description carries the behavioral burden. It adds useful details: the tool acts once, requires observation_id for UI inputs, and select activates a focused label without moving focus. But it omits effects of press/type/launch, return behavior, permissions, or side effects.

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: two sentences, no filler, and the core 'act once, then observe' premise is front-loaded. It sacrifices detail for brevity, but every sentence provides some value.

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?

The tool is complex with 8 parameters and no output schema or annotations, yet the description does not explain return values, how targets are matched, when expected fields are needed, or what happens after each action. Essential context for correct invocation is missing.

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 8 parameters, so the description must compensate. It only adds meaning for observation_id and select, leaving value, device, role, image, expected_app, and expected_label unexplained.

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 indicates the tool performs an action ('Act once') and clarifies the select action, but it never explicitly states that it executes UI actions like press/type/launch on a device or element. It is more than a tautology, yet remains vague and does not clearly distinguish itself from siblings like control or observe.

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?

'Act once, then observe' implies a workflow and 'UI inputs need observation_id' gives a prerequisite. However, there are no explicit when-to-use or when-not-to-use instructions, and no alternatives are named.

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