sylve_backup

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

Annotations already flag destructiveHint=true, idempotentHint=false, and readOnly=false, so the safety bar is lower. However, this tool mixes harmless read actions (targets, jobs, events) with a destructive restore in one entry point, and the description never warns that restore overwrites guest data or that `wait`/`wait_timeout` make calls blocking. That mixed-risk profile is exactly what the description should disambiguate.

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 sentence is waste-free and front-loads the inspection purpose, but at nine words it is drastically undersized for a 7-action, 12-parameter tool. Brevity here trades away necessary structure rather than achieving conciseness.

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 a destructive, non-idempotent tool with nested body object, 25% schema coverage, no output schema, and no per-action contract, the description leaves the agent without the information needed to invoke it correctly. It should at minimum enumerate action modes with their required parameters and flag restore as destructive.

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 25% across 12 parameters, so the description must compensate — and it adds nothing. It does not explain which parameters are required per action (e.g., job_id for run_job, target_id/guest_id/body for restore), nor what `wait`, `wait_timeout`, `limit`, or `node` do at the call level.

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 names a resource (backups) and rough verbs (inspect, run, restore), but it is a single sentence covering a multiplexed tool with seven distinct action modes. Three of those modes (snapshots, event_progress, and the per-job/target/guest scoping) are not signalled at all, and nothing distinguishes it from siblings like sylve_vm_snapshot, sylve_zfs_snapshot, or sylve_replication.

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?

"Inspect ... run or restore" implies a usage, but there is no guidance on when to pick this tool over the ZFS/VM snapshot siblings. It also never says that the `action` parameter selects the mode, so the agent must infer the entire routing logic from the enum alone.

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