Snapshot sandbox

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

Adds substantial behavior beyond the annotations: the source sandbox keeps running, storage is billed until the snapshot is deleted, the call blocks up to 2 minutes, and a large snapshot may still be processing afterward. That last caveat is exactly the kind of async-completion detail an agent needs and that destructiveHint/idempotentHint cannot convey.

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 the core action and result, then layered with scope, billing, and completion caveats in a logical order. Four dense sentences with no outright filler, though the scope clause is slightly compressed for the amount of meaning it carries.

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?

Covers the mutation's side effects, lifetime, restore boundary, and the delayed-readiness problem, with a pointer to sandbox_snapshot_list since no output schema exists. Only minor gap is not saying what the call itself returns (e.g., a snapshot ID) versus what must be discovered via the list tool.

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 67%: name and sandboxId are self-explanatory, but the scope enum is undocumented in the schema. The description fills that gap by defining user (any of your projects), workspace, and project as restore boundaries, which is real added meaning.

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+resource (save a running sandbox as a private snapshot) and the exact contents captured (memory and processes). It also names the downstream consumer (sandbox_create with snapshotId) and the follow-up check (sandbox_snapshot_list), so an agent can place it precisely among the sandbox_* siblings.

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?

Explains the intended use (create a reusable image to start new sandboxes) and clarifies scope semantics and billing lifetime. It does not explicitly contrast with sandbox_fork or sandbox_pause/resume, which are the nearest alternatives, so the when-not guidance is incomplete.

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