Desktop: App

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known; the description adds the real-value context of the desktop_permission prerequisite. However, it never explains the destructive side — e.g. that resize/switch mutate window state or can move a window off-screen — and says nothing about failure behavior if no matching window title is found. With annotations carrying the safety signal, a 3 is appropriate.

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, no waste, with the capability statement front-loaded and the permission requirement demoted to the second position where it belongs.

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?

With 6 parameters, full schema coverage, and a destructive annotation already present, the description covers purpose and the key gating prerequisite. Remaining gaps — window-title matching rules and what happens when a launch target is invalid — are modest for a tool whose parameters are fully self-documenting.

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 enum values are already documented per-property (launch/switch/resize, plus name semantics differing per mode). The description merely echoes the mode list, adding no format details such as whether 'name' needs a full path for launch or a case-sensitive substring for switch. Baseline 3 is correct.

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 set of verbs (launch, resize, bring to foreground) against a clear resource (a Windows application), which separates it from siblings like desktop_click, desktop_type, or desktop_find that act on UI elements rather than windows. It never names a sibling or contrast case explicitly, so it falls just short of a 5.

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 one real guideline is the prerequisite "Requires desktop_permission in the active mission step," which is genuinely actionable. There is no guidance on when to pick this over desktop_find/desktop_click, nor when 'switch' should be preferred over 'launch' if an app may already be running — that ambiguity is left to the agent.

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