vm_backup

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=true, so the safety profile is covered. The description adds real behavioral value beyond that: it discloses the async task model ('Returns task UPID', pointing the agent at task_status) and the downtime implications of each mode ('snapshot' = no downtime). It stops short of stating whether the guest must be running or what happens on failure.

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 operation summary, followed by a compact Args list. Given 0% schema coverage the parameter list is earned rather than padding. The [WRITE] tag is mildly redundant with the destructive annotation but serves as a fast scan cue.

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 5-parameter destructive async write, the description covers purpose, all parameters, mode trade-offs, and the return value (task UPID), with annotations handling safety. With no output schema, the 'Returns task UPID' line is the essential return-value disclosure. Preconditions and failure behavior are the remaining gap.

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 parameter burden and does so well: it defines vmid, storage (with a capability constraint and cross-reference), describes mode's three values including semantics/default, and explains node's auto-locate behavior and target. This meaningfully exceeds the bare schema titles.

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?

Specific verb and resource: 'Create a vzdump backup of a VM/CT to a storage.' This is readily distinguishable from sibling tools like vm_snapshot_create (snapshot vs vzdump backup), backup_restore (restore vs create), and backup_list. The [WRITE] tag immediately frames the operation class.

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?

Usage is only implied by the verb 'backup'. The description routes the agent to storage_list / storage_content for finding a valid storage, which is helpful, but it gives no explicit when-to-use/when-not guidance versus alternatives such as vm_snapshot_create, and no statement of preconditions (guest state, free storage space).

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