GNOME Desktop MCP

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Close a window' implies a destructive action (window termination), but it doesn't specify whether this is reversible, what happens to unsaved content, if it requires specific permissions, or what the expected outcome is. For a potentially destructive tool with zero annotation coverage, this is a critical gap in transparency.

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 extremely concise at three words, with zero wasted language. It's front-loaded with the core action ('Close a window') and doesn't include unnecessary details. For such a simple tool, this brevity is appropriate and efficient.

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?

Given the tool's potential complexity (destructive action with no annotations), the description is incomplete. While an output schema exists (which might cover return values), the description fails to address critical behavioral aspects like safety, reversibility, or prerequisites. For a window management tool among many siblings, more context is needed to ensure correct usage.

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?

The description mentions 'a window' which loosely corresponds to the 'window_id' parameter, but it doesn't explain what a window ID is, how to obtain it, or its format. With 0% schema description coverage (the schema only provides a title 'Window Id' and type 'integer'), the description adds minimal semantic value. Since there's only one parameter, the baseline is higher than for multi-parameter tools, but the description doesn't fully compensate for the lack of schema documentation.

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 'Close a window' is a tautology that restates the tool name without adding specificity. It doesn't distinguish this tool from potential alternatives (like 'minimize_window' or 'unmaximize_window') or clarify what type of window is being closed (application window, browser tab, etc.). While the verb 'close' is clear, the description lacks the context needed to differentiate it from sibling tools.

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 provides no guidance on when to use this tool versus alternatives. With sibling tools like 'minimize_window', 'unmaximize_window', and 'focus_window' available, there's no indication of when closing is appropriate versus minimizing or other window management actions. No prerequisites, exclusions, or alternative suggestions are mentioned.

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