create_sandbox

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

With no annotations, the description carries the full burden of behavioral disclosure and does so strongly: the sandbox is isolated, dedicated, returns only when ready, and is destroyed automatically after timeout_minutes with nothing surviving. It also calls out the pre-installed runtimes, giving the agent a clear model of the environment.

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 description is three sentences with no filler; the core purpose is front-loaded, followed by return behavior, environment details, destruction semantics, and usage guidance. Every sentence contributes distinct information.

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?

The description is complete for the creation act and the environment, but with no output schema it only says 'Returns once the sandbox is ready' without stating what the return value contains (e.g., an ID/handle needed to target subsequent commands). This is a minor gap because sandbox-identification is mostly covered by the name parameter and sibling tools.

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 each parameter is already documented with defaults, ranges, and size mappings. The description mostly re-emphasizes the timeout destruction behavior that the schema already states, so it adds little parameter-level meaning beyond the baseline.

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 uses a specific verb and resource ('Create an isolated cloud sandbox — a dedicated virtual machine you can run commands in') and makes the tool's role obvious relative to siblings like run_command and list_sandboxes. It goes beyond a bare restatement by also describing the preinstalled environment.

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 a clear selection criterion: 'Use this before running any code you would not want to run on the local machine.' This tells the agent when to create a sandbox, but it does not explicitly contrast with alternatives or state when not to use it, so it falls one point short of full guidance.

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