Delete sandbox

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new context beyond that: the deletion is permanent and cascades to all files, it requires user approval, and it does not touch the project or app services.

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?

Four short clauses, front-loaded with the destructive scope, then the approval prerequisite, then the when-to-use, then the exclusion. No filler sentences or redundancy.

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 destructive two-parameter tool with no output schema and full annotation coverage, the description supplies the key behavioral facts an agent needs (permanence, cascade, approval, exclusions). Only failure/error behavior and post-deletion state are unaddressed, a minor gap.

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 50%: sandboxId is documented in-schema (pointing at sandbox_create/sandbox_list) while confirm carries only a const=true constraint with no prose. The description's approval instruction indirectly explains confirm's purpose, but it adds no format or source detail beyond the schema, so the baseline 3 fits.

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 states a specific verb and resource ("Permanently destroy one sandbox and all its files") and explicitly delimits scope by noting it does not delete the project or any app services, which cleanly separates it from sandbox_list/sandbox_show/sandbox_create and from project_delete/service_delete.

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?

It gives clear context ("Use this to clean up a sandbox created for a task") and a prerequisite (get user approval before calling), so the agent knows when it applies. It does not name an alternative sibling for the case where deletion is not intended, so it stops short of explicit when-not guidance.

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