Delete volume

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description goes further: it discloses the detach-then-restart side effect on the app, the 3-day project-trash retention, the irreversibility, and the approval requirement. This is exactly the extra context annotations can't convey.

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 destructive outcome, then packed with conditional clauses that each carry information. The telegraphic fragments ('Without service: a sandbox volume') are dense but readable; no sentence is filler, though the density borders on cramped.

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, yet the description covers side effects, ordering constraints, blockers, and the approval gate for a 4-parameter destructive tool. Nothing an agent needs in order to call this safely 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 100%, so the baseline is 3, but the description adds meaning the schema can't: the presence or absence of `service` selects between two different deletion behaviors, including an app restart. It also reinforces that `confirm` gates on explicit user approval of file loss.

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 ('Permanently delete a volume and every file on it') and immediately disambiguates two operating modes (sandbox volume vs. app volume) that distinguish it from siblings like volume_resize or sandbox_delete. An agent knows exactly what gets destroyed.

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?

Explicit branching guidance: omit service for a sandbox volume, supply it for an app volume, and the two mutual-exclusion rules ('a volume attached to a sandbox can't be deleted, so delete the sandbox first'). It also gives ordering advice (delete the app's volume before the project) and a hard prerequisite (get user approval first).

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