Reinstall OS

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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes well beyond them: it explains that data is destroyed, that snapshots are deleted with no rollback, that dedicated servers erase every disk, that pending snapshot actions block the call, the exact password constraints, and the differing return artifacts (reinstall job ID vs. noty UUID). This is exactly the extra context an agent needs for an irreversible operation.

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 WARNING and destruction consequence are front-loaded, which is the right priority ordering. The paragraph is dense and long, and the platform-specific rules (Cloud/Firecracker vs. Container vs. Dedicated) would scan faster as separated clauses, but nearly every sentence carries an operational constraint rather than filler.

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?

There is no output schema, and the description compensates by describing what each variant returns (job ID for dedicated, noty UUID for VPS) and pointing to get_service_history for completion tracking. Combined with the destructive-action warnings and auth scopes, an agent has everything needed to call this correctly or correctly refuse to.

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 coverage is 100%, so the schema already documents all six parameters, making 3 the baseline. The description adds genuine nuance beyond the schema, notably that dedicated reinstall supports an optional sshKey from list_ssh_keys but "never rootPassword," and restates the confirm flags' user-consent semantics. It does not add much on orderNo or osVersion beyond what the schema says.

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 and resource ("Reinstall OS") plus the exact scope (VPS or qualified dedicated server), which immediately separates it from sibling tools like enter_service_rescue, rollback_snapshot, or restart_service. An agent can identify what this tool does without opening the schema.

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?

Explicit when-to-use and preconditions: read get_os_options.snapshotDeletion first, pass confirmSnapshotDelete only after user confirmation, a pending snapshot action blocks reinstall, and confirmReinstall only after explicit approval. It also names the sibling tools to consult (get_os_options, list_ssh_keys, get_service_history) and states the auth requirements (services:reinstall scope or full-access API key).

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