restore_dns_backup

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe-read profile is covered. The description adds genuinely new context beyond that: recreated records receive new IDs, and forwards are excluded and need separate changes — both important behavioral facts for planning a restore.

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?

Three short, front-loaded statements with no filler. The preview framing comes first, then the ID-churn consequence, then the forwards caveat — each sentence carries distinct information.

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?

An output schema exists, so return values need not be described. The description covers the operation, the backup/plan ID equivalence, and a key limitation, leaving only the unexplained 'domain' parameter and the unnamed apply alternative as gaps.

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 0% for both parameters, so the description must compensate. It usefully clarifies that backup_id is this server's pre-change backup ID and is equivalent to a plan ID, but 'domain' is left completely unexplained (including its string-or-integer union type).

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+resource: previewing a restore of DNS content from a backup ID. The parenthetical '(= plan ID)' ties it to the plan family, giving partial sibling differentiation, but it never names apply_plan as the tool that actually performs the restore, so an agent must infer the preview/apply split.

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 word 'Preview' implies this is a dry-run step used before committing changes, and the note that forwards require separate explicit changes scopes what this call will not cover. However, no alternative tool is named and there is no explicit when-to-use/when-not-to-use statement.

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