Runs a command inside a VirtualBox guest OS and waits for the result, returning output for Bash, sh, PowerShell, or CMD tasks.
Run a command in the guest OS and wait for its result.
| Name | Required | Description | Default |
|---|---|---|---|
| vm | Yes | VM name or UUID | |
| cwd | No | ||
| env | No | ||
| shell | No | Defaults to the guest's default shell | |
| backend | No | auto | |
| command | Yes | ||
| timeoutMs | No | ||
| approvalId | No | Approval ID issued for a previously requested destructive operation |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers only the blocking/waiting trait. It says nothing about what happens on timeout, whether a destructive command requires the approvalId flow, how backend selection (auto/guestcontrol/ssh/winrm) affects behavior, or what permissions are needed to reach the guest OS.
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?
A single front-loaded sentence with no wasted words, which is good structurally. However, the brevity is achieved by omission rather than by efficiency, leaving blocking semantics as the only fact conveyed.
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 an eight-parameter command-execution tool with no annotations and no output schema, the description should explain return shape (exit code, stdout/stderr), timeout behavior, and the approval path hinted at by approvalId. None of that is present, so an agent must guess at execution semantics.
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 only 38%: vm, shell, and approvalId are documented in the schema while cwd, env, backend, command, and timeoutMs are not, and the description adds no meaning for any of them. Given eight parameters, including a nested env object and two enums, the description does not compensate for the coverage gap.
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?
States a specific verb+resource ('Run a command in the guest OS') and adds the synchronous qualifier 'wait for its result', which implicitly distinguishes it from the execute_command_async sibling. It does not name that sibling or get_command_output explicitly, so differentiation is left to inference.
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?
There is no explicit guidance on when to use this versus execute_command_async, wait_for_command, or get_command_output, nor any note about prerequisites such as guest tools, credentials, or approvals. The only cue is the word 'wait', which implies blocking behavior but never states when a non-blocking alternative should be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.