Edit Storage

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

Goes well beyond annotations: discloses the billing consequence of growing, the preview-vs-apply asymmetry, that growing is asynchronous while renames and usage warnings apply immediately, and the operation_id reuse/retry protocol after a timeout. This is consistent with idempotentHint=true and destructiveHint=false.

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-loads the purpose and the action list, then layers constraints, then the confirm flow, then the operation_id protocol. Dense with no filler sentences, though the trailing operation_id paragraph reads as appended boilerplate and the line-wrapped formatting slightly impedes scanning.

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-value detail is unnecessary, and the preview/confirm and async behavior are fully covered. The only meaningful omission is `workspace` scoping and how usage_warning interacts with usage_warning_threshold when passed independently.

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 0% schema description coverage the description carries the load and does so for 7 of 8 params: units for size_gb (GiB), threshold range 0-1, confirm semantics, operation_id UUID convention, storage as pv_name. Only `workspace` is never mentioned, leaving one parameter's meaning to inference.

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 plus resource and enumerates the exact operations (rename, grow, set usage warning) with the console's Edit as an anchor. It also disambiguates `storage` as the pv_name from the storages tool, separating it from siblings like create_storage/delete_storage/connect_storage.

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?

Explicitly defines the two-phase flow: confirm=false returns an estimate and changes nothing, call again with confirm=true after user agreement. It states 'pass only what changes' and warns that storage can grow but never shrink. It does not name a sibling to use instead, but the usage context is unambiguous.

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