Create volume

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

Adds substantial behavior the annotations cannot convey: attaching to an app restarts it with the volume mounted, files survive restarts and redeploys, only one volume per app, and volumes are billed for their size until deleted. This surfaces both the cost consequence and the restart side effect of an otherwise ordinary-looking create call, which is exactly what an agent needs before invoking it.

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?

Tightly front-loaded with the core action first, then the two modes, then billing. The nested parentheticals make the mode sentences dense, but essentially every clause carries a constraint an agent would otherwise get wrong.

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 six-parameter creation tool with full schema coverage, annotations covering mutability/safety, and no output schema, the description covers the remaining gaps: mode selection, placement constraint, defaults, the app restart side effect, and ongoing billing. Nothing material for calling it correctly is missing.

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 already 100%, so the baseline is 3, but the description adds meaning beyond the field blurbs: region must match the target sandbox's region, sizeGb defaults to the project default and is bounded by project limits, and mountPath defaults to /data and only applies with service. Uniqueness of name within a project is never clarified, which keeps it off 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?

States a specific verb and resource ('Create a persistent volume') and then splits the outcome into two concrete modes: a sandbox volume when 'service' is omitted, an app-attached volume when 'service' is given. An agent can tell immediately which shape of resource it gets, and the cross-reference to sandbox_create's volume parameter further disambiguates it from unrelated create tools.

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 explicit conditions for each mode (omit service for sandbox use; provide service for app attachment, one per app) plus constraints: the sandbox volume 'must be in the sandbox's region' and the size 'must be within its limits'. It does not name adjacent tools such as volume_resize or volume_list as alternatives, so routing versus siblings is left partly implicit, but the within-tool decision guidance is clear.

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