start_activity_root

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

No annotations exist, so the description carries the full burden; it does disclose the two most important behavioral facts — root privilege is required and the normal exported=false restriction is bypassed. It says nothing about failure behavior (missing package, non-existent Activity), whether root absence causes an error or fallback, or side effects of the launch on app state.

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, front-loaded with a bracketed label and the core capability, which is good structure. However the exclamation marks and promotional phrasing ('强行穿透', '繁琐的开屏广告与多级菜单跳转') trade precision for marketing tone rather than stating constraints.

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?

An output schema exists and all seven parameters are documented in the schema, so return-value explanation is not required. For a root-level, security-bypassing launcher with zero annotations, the description is thin on preconditions (root availability, app installed) and on what the caller should do after launch.

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 100%, so the parameters (action, extras, package, activity, data_uri, return_ui_after, force_stop_first) are already fully self-documenting. The description adds conceptual context about targeting private activities and DeepLinks but no syntax, format, or precedence rules beyond the schema.

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 action (force-launch an Activity via root) and a concrete target class (internal private activities with exported=false, or DeepLink schemes), so an agent knows exactly what the tool does. It does not differentiate itself from closely related siblings such as send_intent or app_action, which leaves ambiguity about which tool owns plain intent dispatch.

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 benefit statement about skipping splash ads and multi-level menu navigation, which hints at the 'reach a deep screen fast' scenario. There is no explicit when-to-use / when-not-to-use rule and no named alternative (e.g. send_intent for normal exported intents, ui_snapshot to verify the landing page).

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