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

The description discloses behavioral details beyond the sparse annotations: the state changes to 'ending', queued work drains, and no allowance is refunded. It sets expectations about side effects, which is particularly valuable since annotations are minimal and do not indicate any of these specifics.

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, front-loaded with the primary action and state transition. The allowance clarification is useful but slightly tangential. Overall, it is compact and well-structured with no fluff.

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 covers the core behavior and side effects, but the missing explanation of the required wallet_address parameter leaves a gap. For a simple tool with one parameter and no output schema, this omission prevents full self-sufficiency, though the rest of the context is adequately provided.

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?

The single required parameter, wallet_address, is not explained at all in the description. Schema description coverage is 0%, so the description carries the full burden for parameter semantics, but it only mentions 'user's session sandbox' without connecting it to the parameter. The agent is left to infer that wallet_address identifies the sandbox session, which is risky.

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 exactly what the tool does: 'Stop the user's session sandbox gracefully' with a specific state transition ('ending') and behavior (queued work drains). This is a specific verb-resource pair and clearly distinguishes it from siblings like sandbox_start, sandbox_status, and sandbox_keepalive.

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 gives clear usage context: 'a stopped sandbox is good hygiene when the work is done.' It also clarifies a common misconception that stopping frees allowance. However, it does not explicitly mention when not to use it or name alternative tools, though the sibling names make that obvious.

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