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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the crucial context that state persists ('storage kept') and that the next resume_app becomes a cold start, which is exactly the consequence an agent needs. It also resolves the apparent tension with destructiveHint=false by clarifying that no storage is lost, and discloses the error path.

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?

Three short sentences, each load-bearing: the action, the required prerequisite, the post-state consequence, and the error condition. The primary action is front-loaded with no filler.

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 single-parameter tool with no output schema, the description covers prerequisite sequencing, resulting state, and failure behavior, which is everything needed to invoke it correctly. Nothing material is left to inference.

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?

Only one parameter, and the schema already documents it at 100% coverage ('Session from open_app'). The description adds no further detail about the session value or where it comes from beyond what the schema states, so baseline 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?

States a concrete verb and resource ('Swipe the app's card away in the app switcher') that is unmistakably distinct from siblings like resume_app, switch_app, and open_recents. An agent can identify the exact UI action being performed without consulting the schema.

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 explicit precondition ('call open_recents first') and the failure mode when it is unmet ('Fails with recents_not_open otherwise'), which is stronger than most siblings. It stops short of explicit when-not-to-use guidance, e.g. contrast with end_session or when killing is preferable to simply switching.

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