pdm_pve_lxc_power

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

With no annotations provided, the description carries full burden. It discloses the mutation nature ('MUTATION'), dry-run behavior, confirm requirement, and task-backed output ('submitted'). However, it omits details like required permissions, idempotency, or state-change consequences, which are important for safety.

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 extremely concise—two short sentences and a header—with no wasted words. It front-loads the mutation intent and provides critical usage details efficiently.

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?

Given the tool's simplicity (5 parameters, no nested objects) and the presence of an output schema, the description covers key behavioral aspects. It lacks prerequisites (e.g., container existence) and error conditions, but for a power control tool, the provided information is sufficient for safe use.

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 low (20%). The description adds meaning for the 'confirm' parameter (dry-run bypass) and implies action values (start/stop/shutdown). It does not describe 'vmid', 'remote', or 'proximo_target' beyond what the schema provides, leaving gaps in parameter understanding.

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 tool is for starting, stopping, or shutting down a container on a PDM-registered remote, using the verb 'start/stop/shutdown' and the resource 'container'. It distinguishes itself from sibling tools like pdm_pve_qemu_power (for VMs) and other lxc tools (config, list, migrate, snapshot) by specifying the domain and actions.

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 explicitly mentions the dry-run default and the need for confirm=True to submit, providing clear context on when to use the confirm parameter. While it does not explicitly state when not to use this tool or mention alternatives, the domain-specific nature (PDM vs direct PVE) limits ambiguity.

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