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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is partly covered. The description adds materially: crash-consistency, storage location off-host, the default 7-day retention, an explicit latency note (waits up to a minute), and that delete removes both the metadata and the stored copy. It does not distinguish which of the five actions are safe reads versus mutations, a notable gap for a multi-action tool, keeping it at 4.

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 one-line scope statement is front-loaded, followed by a compact per-action breakdown that mirrors the enum. The telegraphic style (e.g. 'kept retentionDays', 'each as get gives it') packs a lot in without filler, though it demands careful reading and the sentences are dense rather than crisp.

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?

With no output schema, the description carries the return burden and does so — get returns state, size, stored bytes and expiry, and list returns items shaped the same way. All five actions and most parameters are addressed. Missing pieces are minor: the destructive/read distinction per action and limit/state semantics, both partly covered by the schema.

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 only 40%, so the description must compensate, and it largely does: it explains name?, retentionDays (defaults to the volume's retention, 7), cursor usage (pass nextCursor back), volumeId scoping, daily on/off, and what id identifies. It adds real meaning over the bare schema. limit is left to the schema and state is only implied as a filter, which prevents a 5.

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 opening states a specific resource and scope — crash-consistent backups of a volume kept off its host — and enumerates all five actions (create, list, get, policy, delete) with what each does. It also distinguishes itself from the runtime_volumes sibling by naming the restore path (runtime_volumes action create with fromBackup), so an agent can route correctly without opening schemas.

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?

Each action carries contextual guidance: create for an immediate backup (waits up to a minute), list for browsing your backups newest-first, policy for enabling/disabling daily backups, and delete for removal. The restore alternative is explicitly named and routed to runtime_volumes. It lacks explicit when-not guidance or prerequisites (e.g. the volume must exist), so it stops short of a 5.

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