perform_system_action

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

No annotations are provided, so the description carries the full behavioral burden. It implies the effect of each action (navigate back, go home, open recents) but says nothing about permissions, side effects, reversibility, or device state requirements for what is a mutating UI operation.

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?

A single, front-loaded sentence with no padding. It is efficient, though the brevity contributes to the missing usage and behavioral detail.

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 one-parameter tool with an output schema, the core action set is conveyed. However, with zero annotations it omits permission/side-effect context and any routing guidance among the many sibling interaction tools.

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 'action' parameter is already documented with the same values (BACK/HOME/RECENT_APPS) in the schema. The description adds no meaning beyond the schema, so the baseline of 3 applies.

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 verb (执行/execute) and resource (系统级操作/system-level actions), and enumerates the concrete actions: back, home, recent tasks. It does not name or contrast a sibling tool (e.g., tap_screen or long_press), so it stops short of full differentiation.

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?

Usage is only implied through the action examples; there is no explicit when-to-use guidance, no exclusion of overlapping siblings like tap_screen/swipe_screen, and no stated preconditions.

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