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

Annotations only declare this is not read-only and not destructive; the description goes further by naming the resulting AppState ("active"), promising that the current screen is kept, and disclosing the specific error code returned on misuse. It does not cover what happens if the session is stale or the app was killed, but for a single-step resume it is well above the annotation baseline.

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 compact sentence front-loads the effect, then the resulting state, then the failure mode, in that order. The home-screen/app-switcher framing is metaphorical rather than literal for an API caller and costs a few words, but it does clarify semantics without bloat.

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 one-parameter state-transition tool with no output schema, the description covers the effect, the post-state, screen preservation, and the error case. Only the behavior when the session is invalid or the app is no longer installed is left unaddressed.

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?

With one parameter at 100% schema coverage, the schema already documents 'session' including its origin ('Session from open_app'). The description adds no further constraint or format detail on the session argument, so the 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?

The description states a specific verb and resource: bringing a backgrounded app back to the foreground with its screen preserved, ending in AppState "active". It is distinguishable from a cold launch, but it never names its nearest siblings (open_app, switch_app, kill_app), so the boundary is inferred rather than stated.

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?

It gives a clear use context (the app exists in the app switcher/background) and an implicit when-not-to-use via the failure mode 'app_in_foreground' if the app is already in front. What is missing is explicit routing against alternatives such as open_app or switch_app when the app is not currently backgrounded.

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