window_list

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds valuable context beyond annotations by noting that the VM remains locked and the user must call vm_unlock afterward, which is critical for session state management.

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 with no filler. The first sentence front-loads the output fields, and the second conveys the essential lock/unlock workflow. Every word 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?

The description covers return fields and the critical lock context, but it omits any explanation of the visible_only parameter. Since there is no output schema, this gap is significant enough to make the description only minimally complete.

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 only parameter visible_only is not mentioned in the description, and the schema provides no description coverage (0%). The agent must infer its semantics purely from the name, which is insufficient for correct invocation.

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 lists windows and enumerates the exact metadata returned (handle, title, class, process, visibility, enabled state, screen rectangle). This distinguishes it from sibling tools like window_focus or window_capture by specifying its output scope.

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 clear context that the VM remains locked by this session and instructs to call vm_unlock when finished. While it does not explicitly name alternatives or state when not to use it, the listing purpose is unambiguous and the workflow context is useful.

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