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

With no annotations provided, the description carries the full burden and delivers: irreversibility, exactly what is destroyed (files, packages, background tasks, memory), billing consequences (per-second with 60 s minimum for ephemeral, per-started-hour for persistent), and the auth prerequisite ('Requires: token').

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?

The critical warning is front-loaded with strong emphasis, and every clause is information-bearing. The billing parenthetical is slightly dense, but it earns its place for a destructive operation.

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 single-parameter destructive tool with no output schema, the description covers safety, data loss, billing, prerequisite action, and auth — nothing an agent needs before invoking it 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 100% and the sole sandbox_id parameter is fully documented in the schema, including its pattern and provenance. The description adds no parameter-level detail, so the baseline of 3 applies.

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 (Delete) and resource (sandbox), and immediately scopes it ('running or paused'), letting an agent distinguish it from siblings like create_sandbox, get_sandbox, or kill_task without opening a schema.

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 explicit actionable guidance ('download_file anything you need first') and states the tool applies to both running and paused sandboxes. It stops short of naming alternatives or a when-not-to-use condition (e.g., versus cancel_service), but the destructive-selection context is clear.

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