desktop_launch

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description still adds genuine value by disclosing that Electron/Node-injection environment variables are stripped before launch and that the call waits for a window, which an agent could not infer otherwise. It omits failure modes, whether the wait is blocking, and what happens when the target is not found, so it sits at solid-but-partial.

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 front-loaded sentence that leads with the action and target forms before the behavioral clause about env stripping and window waiting. No filler, though the density means several distinct behaviors are compressed into one clause.

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 seven-parameter tool with no output schema and mutation-like side effects, the description leaves too much unsaid: no return information, no timeout or failure behavior, and no explanation of the majority of parameters. What it does say about env-var stripping and window waiting is useful but does not make the definition complete enough to call confidently.

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 only 14% across seven parameters, so the description must carry the load and largely does not. It does map the target parameter to its accepted forms and implicitly touches kind='store' via 'Store app' and wait/verify behavior via 'wait for its window,' but cwd, arguments, refresh, wait_seconds and verify_window are never explained anywhere.

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 opens with a specific verb-plus-resource, 'Launch a Windows application,' and enumerates the accepted target forms (executable path, Start Menu display name, URL, Store app), which is enough to separate it from siblings like desktop_click or desktop_type. It stops short of naming any sibling or stating a boundary explicitly, so it is clear but not differentiated by comparison.

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?

There is no when-to-use guidance, no prerequisite or permission statement, and no mention of alternatives such as desktop_actions or desktop_windows for interacting with an already-running app. The only hint of usage context is the phrase 'wait for its window,' which is a behavior clause rather than routing guidance.

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