window_close

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the close action's destructive nature is covered. The description adds value beyond annotations by disclosing that the VM lock persists after closing and that vm_unlock is required as a follow-up.

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 concise sentences: the first states the core action, the second provides the essential follow-up requirement. There is no wasted wording, and the most important operational detail (vm_unlock) is included.

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 simple two-parameter action with no output schema, the description is mostly complete: it states the action, references the selected window, and notes the lock behavior. It omits explicit failure/return behavior, but the schema covers parameter origins and the lock hint provides critical operational context.

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?

Schema description coverage is 100%, with both vm_name and window_id already documented. The description does not add meaningful parameter semantics beyond what the input schema provides, so the baseline score of 3 is appropriate.

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 action ('close') on a specific resource ('selected window'), clearly distinguishing it from sibling tools like window_focus, window_capture, and window_list. It is immediately obvious what this tool does.

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 workflow context: the VM remains locked by this session and vm_unlock must be called when finished. It does not explicitly name alternative tools or when-not-to-use conditions, but the lock and unlock sequencing gives the agent actionable usage guidance.

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