open_desktop

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

No annotations are present, so the description carries the full burden. It discloses the blocking behavior ('wait until its Desktop Bridge answers or waitForBridgeSec lapses'), the console-window-free spawn, the return contract ('pid + bridge availability + manifest'), and degradation on timeout ('the Desktop itself may still be healthy'). This is rich safety-conscious behavioral disclosure.

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?

The description is dense but front-loaded with the critical 'UNSAFE-FOR-PIPELINE' warning. It packs a lot of information into one long sentence with semicolons and dashes, which is efficient but slightly run-on. It could be split into two sentences for readability, but every clause earns its place.

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 tool with no output schema and no annotations, the description is remarkably complete: it covers the launch mechanism, install variants, window behavior, timeout handling, return values, and explicitly states what happens when the bridge isn't available. It also provides safety context for pipelines. There are no significant gaps for an interactive attach tool.

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 covers 100% of parameters, giving a baseline of 3. The description adds value by explaining the exePath probing behavior ('standard MSI install, the WindowsApps Store layout or the Store execution alias') and clarifies waitForBridgeSec's deadline semantics ('no bridge by the deadline degrades to a clear entry'). This goes beyond the schema's simple type/default descriptions.

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 clearly states the tool 'launch[es] Power BI Desktop on a .pbix/.pbip' and waits for the Desktop Bridge. It uses a specific verb ('launch') with a specific resource type, and the 'UNSAFE-FOR-PIPELINE' marker and mention of unattended pipelines distinguish it from sibling tools like bridge_reload or bridge_status.

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?

Explicitly warns 'UNSAFE-FOR-PIPELINE (interactive attach only)', telling agents when NOT to use it, and provides an alternative: 'Unattended pipelines must keep using their own queue-managed launch.' This is clear when-to-use/avoid guidance.

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