Create Sandbox

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

Annotations provide only basic hints (not read-only, not idempotent). The description adds that the sandbox boots and persists, but does not disclose side effects like resource consumption, error behavior, or lifecycle details beyond stopping.

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?

Two sentences, no wasted words, front-loaded with the core action. Highly concise while covering purpose and key behavioral trait (persistence).

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 tool has 12 parameters including complex nested objects (volumes, patches) and no output schema. The description is too brief, omitting what the return value is, how to reference the created sandbox, or how 'full configuration' maps to the rich parameter set.

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 all parameters have descriptions in the schema. The description does not add additional meaning beyond 'full configuration,' so it meets the baseline but provides no extra value.

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 clearly states the tool creates and boots a persistent sandbox with full configuration. It uses specific verbs ('Create and boot') and distinguishes from sibling tools like sandbox_run or sandbox_exec by emphasizing persistence and full configuration.

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?

The description mentions the sandbox 'stays running until explicitly stopped,' implying use when a persistent sandbox is needed. However, it provides no explicit guidance on when to use alternatives (e.g., sandbox_run for ephemeral tasks) or when not to use this tool.

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