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

Adds substantial behavior beyond the annotations: delete 'refused while a sandbox holds it' and destroys 'all its data' while backups persist for their retention; one sandbox mounts read-write at a time; daily off-host backup unless turned off; backedUp true only once a checked copy is off host. These are exactly the destructive/prerequisite details an agent needs and annotations alone do not carry.

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?

Front-loaded with the resource definition, then structured action-by-action in a compact form with no filler sentences. The action(...): value notation is dense enough to occasionally slow parsing, but every clause earns its place.

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?

No output schema exists, so the description appropriately describes returns: get yields 'state, size, space used, attachments and backups', list returns 'each as get gives it' newest-first, and backedUp is explained. Missing only coverage of the state enum and idempotencyKey retry semantics for a 10-parameter tool.

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?

With only 30% schema description coverage, the description carries the load and does so for the key params: sizeMiB and fromBackup semantics, name/region on create, cursor/nextCursor pagination, and the id used by get/delete. Gaps remain for state (enum values), idempotencyKey, and limit despite their importance for list.

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?

Names the resource concretely ('persistent disks that outlive sandboxes') and enumerates the four supported actions (create/list/get/delete) with per-action semantics. It is clear what the tool does, but it never names or routes to the sibling runtime_volumes_backup even though backups feature heavily in the text, so sibling differentiation is incomplete.

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?

Gives actionable context per action: provide 'sizeMiB, or fromBackup to restore one', 'Pass nextCursor back as cursor', and notes creation-side attachment via 'volumes: [{volumeId, path}]' on sandbox create. It stops short of stating when this tool should be preferred over runtime_volumes_backup or the sandbox mount tools.

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