Start, stop, shut down, reboot, or restart one or more virtual machines by name or RID, optionally targeting a cluster node or waiting for completion.
Start, stop, shutdown, reboot, or restart one or more VMs by name or RID.
| Name | Required | Description | Default |
|---|---|---|---|
| vms | Yes | ||
| node | No | Target cluster node hostname or UUID. Omit for cluster-wide. | |
| wait | No | ||
| action | Yes | ||
| context | No | Named login context from ~/.config/sylve/config.yaml. | |
| wait_timeout | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered structurally. The description adds the useful behavioral fact that this is a batch operation over multiple VMs, but says nothing about whether 'stop' is a hard kill, whether waiting is blocking, or whether partial failures roll back.
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?
One sentence with zero waste, front-loading the action set ahead of the resource and identifier forms. Nothing is padded or redundant.
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 destructive, non-idempotent batch mutation with no output schema and two-thirds of parameters undocumented, the description is far too thin. An agent cannot tell whether the call blocks for wait_timeout seconds, whether it targets cluster-wide by default when node is omitted, or what a partial failure looks like.
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?
At 33% schema coverage, the description must compensate and does not. It only reinforces the vms identifier format; node, wait, wait_timeout and context are given no meaning at all, and even the schema leaves 'wait' and 'wait_timeout' completely undocumented despite wait defaulting to true and wait_timeout defaulting to 60.
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 set (start, stop, shutdown, reboot, restart) and resource (VMs), plus the batch scope 'one or more' and the identifier forms 'by name or RID'. This clearly separates it from sylve_vm_create, sylve_vm_delete, sylve_vm_migrate and from the parallel sylve_jail_action, though it never names a sibling explicitly.
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?
No when-to-use or when-not-to-use guidance. Critically, the five actions are listed but not differentiated: stop vs shutdown vs restart vs reboot have materially different semantics (force vs graceful) and an agent must guess which to pick, as well as what happens when 'one or more' VMs partially fail.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.