List Windows

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

Beyond the readOnlyHint and destructiveHint annotations, the description adds that the tool requires Accessibility permission, which is important behavioral context. It also clarifies the scope ('all on-screen windows') and the nature of the windowHandle ('opaque'). The description goes beyond annotation safety and gives practical operational details without contradicting the annotations.

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 two sentences: the first states the action and the output fields, the second provides the permission requirement and usage context. Every word adds value, with no redundancy or filler. It is appropriately sized for the tool's simplicity.

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 simplicity (no params, no output schema), the description covers all its essential aspects: what it returns, the permission requirement, and how the result connects to other tools. There is no missing information that would leave an agent uncertain about invocation or expected output.

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 tool has zero parameters, and the schema is empty. The baseline for 0 params is 4. The description does not need to explain parameters; it focuses on output fields, which is appropriate. Since there are no parameters, the description fully covers what the agent needs to know about inputs (that there are none).

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 states a specific verb and resource: 'List all on-screen windows'. It enumerates the return fields (title, owning app, pid, bounds, layer, minimized state, windowHandle) and distinguishes itself from sibling tools by focusing on the complete window list rather than active/capturable windows. The reference to passing windowHandle to other window tools further clarifies its role.

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 implies when to use the tool: when you need an overview of all windows or need a windowHandle for subsequent window operations. It mentions a prerequisite (Accessibility permission) and explains the handle is meant for window_focus/window_set_state/window_move/window_close. It does not explicitly contrast with alternatives like window_get_active or list_capturable_windows, so it lacks explicit exclusions.

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