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 covered. The description adds meaningful behavior beyond annotations: backups are crash-consistent and off-host, create waits up to a minute, list returns newest first with cursor paging, policy controls automatic retention/schedules, and delete removes both the backup and its off-host copy. It does not describe authorization requirements or failure/error behavior, which keeps it from a 5.

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 description is dense but well organized: one front-loaded summary sentence, then each action introduced by its signature and a compact behavior note. Multiple complex actions are covered without filler or repetition, and each sentence contributes operational meaning.

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 12-parameter, multi-action, nested-schema tool with no output schema, the description is substantially complete: it explains get/list outputs, create timing and retention, policy schedule semantics, and delete scope. It still leaves create's return shape, idempotencyKey usage, state transitions, and error handling to the schema or inference, so it is not fully complete.

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 50%, so the description carries real weight and mostly succeeds: it maps volumeId, name, retentionDays, cursor, limit, state, schedule, daily, and keep to specific actions, and gives schedule and keep examples plus the default retention behavior. It omits idempotencyKey and does not explain state enum meanings or limit handling in detail, so some parameter semantics remain schema-only.

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 opens with a specific verb-and-resource statement: crash-consistent backups of a volume kept off its host. It then names all five actions (create, list, get, policy, delete), making the backup scope clearly distinct from volume-management siblings. An agent can identify the tool's purpose 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?

The action signatures implicitly define when to use create, list, get, policy, and delete, and the description explicitly routes restore usage to runtime_volumes action create with fromBackup. It does not give explicit exclusions or decision rules for every case, such as when to use list versus get or when policy is preferable to ad-hoc create, so it is strong but not fully exhaustive.

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