snapshot

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

With no annotations provided, the description carries full burden. It explains that the tool saves state (non-destructive), captures only packages and system state (not /workspace), and returns a confirmation or error. It lacks details on auth or rate limits but is sufficient for a save 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?

The description is concise and front-loaded with the purpose. It uses a structured Args/Returns format, includes examples, and every sentence adds value without 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?

Given the tool has an output schema (though not shown), the description need not detail return values. It covers the core behavior, parameters, and key constraints. It could mention idempotency or overwrite behavior, but is otherwise complete.

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 0%, so description must compensate. It explains snapshot_name as a name for the snapshot with examples, and sandbox as the named sandbox with a default of 'default'. This adds meaning beyond the schema's plain field titles.

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 starts with a clear verb+resource: 'Save the current sandbox state as a reusable snapshot image.' It specifies what is captured (installed packages and system state) and what is not (/workspace files), distinguishing it from sibling tools like restore, delete_snapshot, and list_snapshots.

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 implies when to use (creating reusable snapshots) and provides example names ('with-pytorch', 'ml-env'). It does not explicitly state when not to use or compare with alternatives, but the sibling context covers related operations.

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