window_capture

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

Beyond the readOnly, idempotent, and non-destructive annotations, the description discloses an important behavioral trait: the VM remains locked by this session and requires a later vm_unlock call. This adds meaningful operational context that the annotations do not convey.

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 concise sentences that front-load the core action and output type, then add the lock-related operational note. Every sentence adds necessary information with no redundancy or filler.

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 two-parameter tool, the description covers the return format (MCP PNG image content) and the important post-condition (VM remains locked, call vm_unlock). The schema handles parameter documentation, and annotations cover safety, making the definition complete for an agent to invoke it correctly.

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 coverage is 100%, with both vm_name and window_id already described clearly in the schema. The description adds no additional parameter-level detail, so it neither improves nor harms parameter understanding beyond the structured schema.

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 uses a specific verb and resource: 'Capture a selected window' with a specific output type, 'native MCP PNG image content.' It clearly distinguishes itself from the sibling screen_capture and qemu_screen_capture tools by focusing on a window rather than the full screen.

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: use this tool when you need an image of a specific window. It also gives workflow guidance by noting that the VM remains locked and that vm_unlock should be called afterward. It does not explicitly name alternative tools or exclusions, but the intended use is not ambiguous.

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