pbi_close_desktop

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

Beyond the destructiveHint annotation, it explains that only the instance with that file is closed, verified by process name + start time (never PID alone), and re-checks afterward via `verified_closed`. It warns that unsaved changes are lost, including refreshed session data in .pbip, and requires `confirm=true`.

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 moderately sized but well-structured, with each section serving a purpose: action, rationale, verification behavior, and destructive warning. It is not overly verbose for a destructive tool, though it could be tightened.

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 destructive close operation, it covers the key context: when to use, what happens, consequences, and return indicators. Minor gaps exist around error handling (e.g., insufficient permissions or multiple instances with the same file), but the overall picture is complete for an agent to invoke it correctly.

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 0% schema description coverage, the description compensates partially: it explains `confirm` is required for the destructive action and mentions return fields (`verified_closed`, `was_open`). However, it does not explicitly describe the `path` parameter format or the `request_id` role, leaving some ambiguity.

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 and resource: 'Cierra la instancia de Power BI Desktop que sirve ESE proyecto' (closes the Power BI Desktop instance serving that project). It clearly distinguishes this from sibling tools like pbi_open_in_desktop by positioning it as the missing exit in the edit-open-look-edit cycle.

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 states when to use it: writing TMDL requires Desktop closed, and this tool is the missing way to close it from here, contrasting with manually killing the process in PowerShell. It also notes it does nothing if the file isn't open, providing a no-op safety condition.

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