Send keystrokes to Parallels VM

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

Annotations already convey that this is a non-read-only, destructive, open-world operation, so the description does not need to repeat those warnings. It adds useful behavioral detail: keystrokes are 'synthetic', the target must be a 'running VM', multiple keys can be sent 'in order', and delay_ms controls delay 'between key events'. This goes beyond the structured fields without contradicting them.

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 front-loaded with the core action and then uses compact bullet lists to enumerate supported inputs and parameters. Every listed example earns its place by illustrating valid input forms. It is detailed enough to be useful without being padded.

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 3-parameter tool with an output schema, this description covers the operation, parameter semantics, accepted input shapes, and sequencing. It could be more complete by noting error conditions (e.g., VM not running) or clarifying that keystrokes go to the guest's active session, but these are minor gaps given the annotations and examples.

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 0%, so the description carries the full burden for explaining parameters. The Args section provides clear semantics for all three parameters: vm as name or UUID, keys as a key name/chord string/list of keys, and delay_ms as the inter-event delay with a default. This fully compensates for the otherwise bare 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 opens with a specific verb and resource: 'Send synthetic keystrokes or hotkey combinations to a running VM.' It clearly distinguishes this from sibling tools like vm_exec and vm_copy_to_guest by focusing on keyboard input rather than command execution or file transfer. The supported input forms and examples further reinforce what the 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 implies usage through examples and supported input types, and the constraint 'to a running VM' gives some context. However, it does not explicitly state when to prefer this over vm_exec or when not to use it, nor does it mention prerequisites like the VM needing a visible desktop or the impact on foreground applications. Usage guidance is adequate but mostly implicit rather than explicit.

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