window_list

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

With readOnlyHint/idempotentHint/destructiveHint already present, the description adds a meaningful behavioral caveat: the VM remains locked by this session and requires a subsequent vm_unlock. This is not inferable from the annotations and prevents the agent from finishing without releasing the lock. It could additionally mention pagination or empty-result behavior, but the lock note is strong.

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?

Two sentences: the first states the operation and return fields, the second states the lock caveat. No filler or restatement of the schema.

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 is mostly complete for a low-complexity read-only tool: it enumerates return fields and the lock/unlock workflow. However, with no output schema and an undocumented visible_only parameter, the definition lacks enough detail for confident invocation with the optional parameter. Minor error/empty-result behavior is also unspecified.

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 schema documents vm_name clearly, but visible_only has no schema description and the tool description never mentions it. The phrase 'visibility' refers to a returned field, not the filter parameter, so an agent is left to infer what visible_only=false does. At 50% schema coverage, the description needed to compensate and did not.

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?

Description opens with 'List windows' and enumerates the exact attributes returned (handle, title, class, process, visibility, enabled state, screen rectangle), so the tool's action and output are unambiguous. This clearly separates it from sibling window_focus/window_close/window_capture, which mutate or capture rather than enumerate.

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 gives important lifecycle context: the VM is locked by this session and vm_unlock should be called when finished, which helps an agent understand where this call fits in a locked-VM workflow. It does not explicitly say when to prefer this over alternatives such as process_list or window_capture, so the guidance is contextual rather than comparative.

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