bucket_delete

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

Annotations already declare destructiveHint=true, but the description adds substance beyond them: irreversibility, the verifiably-empty precondition, the scope of the emptiness check, and the no-mass-delete guarantee. This is exactly the behavioral context an agent needs before an irreversible operation.

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 [WRITE][risk=high] and the irreversibility warning, then usage guidance, then args. No sentence is filler; even the emptiness-check sentence earns its place by preventing an agent from assuming it can force-delete.

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 high-risk mutation with no output schema and zero schema coverage, the description covers safety, precondition, preview path, parameter provenance, and target resolution. Nothing an agent needs in order to call 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 description coverage is 0%, so the description must compensate, and it does: bucket_name's provenance is given (from bucket_ls), dry_run's preview semantics are defined, and target's fallback to the default is explained. Every parameter gains meaning unavailable in the bare schema.

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 (Delete) and resource (a bucket), plus a crucial behavioral constraint: it is refused unless verifiably empty. This distinguishes it from bucket_create and from sibling object-level deletion paths; an agent knows exactly what this does.

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 offers dry_run=True to preview before committing, and states the tool will never mass-delete to force a bucket empty. It also tells the agent that noncurrent versions and delete markers count toward emptiness, which shapes when to use remove_incomplete_uploads or object-level cleanup first.

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