sandbox_list

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

With no annotations supplied, the description does the heavy lifting: it discloses that one entry is returned per sandbox, names the fields (sandbox_id, network mode with the exact allowed values "none"/"nat", status, age in seconds), and states the empty-list case. It omits any mention of pagination, result caps, or whether stopped sandboxes are included, which are meaningful gaps for a listing tool with no safety annotations.

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, followed by usage triggers, then return shape, then the empty case. Every sentence carries distinct information and there is no redundant phrasing.

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?

An output schema exists, so the description is not obliged to enumerate return fields, yet it does so concisely and adds the semantics of the age field (seconds) and the empty-result case. The main unresolved ambiguity is scope — "currently exist" leaves unclear whether stopped or exited sandboxes appear in the listing.

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 tool takes zero parameters, so there is no parameter semantics to explain beyond what the empty schema already conveys. The description correctly adds no parameter noise and instead spends its words on the return shape.

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 and resource ("List the sandboxes that currently exist") and names the practical outcomes: recovering a lost sandbox_id or auditing old sandboxes for destruction. It does not explicitly contrast itself with sandbox_check, the closest sibling, so an agent must infer that check operates on a single known sandbox rather than enumerating all of them.

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?

Gives concrete triggering conditions — "use this to find a sandbox_id you lost track of, or to check whether old sandboxes should be destroyed" — which implicitly routes toward sandbox_destroy for cleanup. There is no explicit when-not or disambiguation from sandbox_check, so the guidance is clear but not exhaustive.

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