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

Annotations only declare that this is not read-only and not destructive; the description adds the important behavioral fact that the app is backgrounded rather than closed and that a card is presented. That is meaningful state-change context an agent would otherwise have to guess at. It does not describe what the call returns or any preconditions (e.g., whether an app must be in the foreground), which keeps it below a 5.

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 short sentences, front-loaded with the action and effect, followed by sibling disambiguation. Every clause carries information and nothing is redundant.

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 UI action with annotations present and no output schema, the description covers the effect, the state transition, and how it relates to resume_app and kill_app. Only minor omissions remain, such as whether an app must currently be open or what the tool returns when the switcher is already showing.

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?

There is a single required parameter and schema description coverage is 100%, so the schema already explains that 'session' comes from open_app. The description adds no meaning beyond that, which is the baseline-3 case when the schema does the work.

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 specific verb and resource ('Open the app switcher') and immediately describes the concrete effect: the app goes to the background and its card is shown. It also names two siblings (resume_app, kill_app) with their distinct behaviors, so the agent can separate this tool from them without inspecting the schemas.

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?

The description frames the switcher as the step whose card can then be resumed or swiped away, effectively telling the agent to use resume_app or kill_app rather than this tool for those outcomes. It stops short of an explicit conditional statement ('use this only when you want to reveal the switcher'), so the routing is clear but slightly inferential.

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