ct_start

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

Annotations already declare destructive/non-idempotent writes, lowering the bar. The description adds real context beyond them: the return value (task UPID) and the dry_run preview option that lets the agent dry-run before mutating.

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?

Front-loaded with the [WRITE] tag, action, return value, and inverse before the preview note and args. Every line earns its place with no redundancy.

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?

Covers the mutation, return value, preview mechanism, and every parameter despite no output schema or schema descriptions. Adequate for correct invocation; only the UPID's downstream consumption and node/target interaction are left implicit.

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?

With 0% schema coverage, the description must carry the load and mostly does: vmid (numeric id, points to ct_list), dry_run (preview), target (config name), node (omit to auto-locate). All four params get meaning, though formats remain loose.

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?

Names a specific verb+resource ('Start an LXC container') and disambiguates from the VM sibling by scoping to LXC. It also names the inverse operation (ct_stop) and states the return value (task UPID), so an agent can place it precisely among siblings.

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?

Gives clear operational context: the inverse relationship to ct_stop and the dry_run=True preview path. It doesn't explicitly contrast with vm_start or state when-not to use, so it stops short of full alternative routing.

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