window_capture

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds critical behavioral information: the VM is locked by this session and must be unlocked via vm_unlock. It also discloses the return format (native MCP PNG image content), which is not in the annotations. No contradiction with annotations is present.

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, front-loaded with the primary action and output, followed by a crucial lock/unlock note. Every word adds value with no repetition 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 single-parameter tool with no output schema, the description covers the action, output type, and a critical lifecycle requirement (unlock). The lock behavior is essential context that would be otherwise unknown. This is complete for the tool's complexity.

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 input schema has 100% coverage with a description for window_id ('Window handle returned by window_list'), so the schema already provides full parameter meaning. The description adds no extra parameter-level detail beyond what the schema states, meeting the baseline expectation without enhancement.

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 action ('Capture a selected window') and the resource (a window), with the output format specified as 'native MCP PNG image content'. It distinguishes itself from siblings like screen_capture (whole screen) and window_list (listing windows) by focusing on single-window capture.

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 after capture and that vm_unlock must be called when finished, indicating a precondition and follow-up action. It does not explicitly name alternatives or state when not to use this tool, but the context is clear enough for an agent to decide to use it when capturing a specific window.

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