fork_sandbox

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: parent session untouched, sandbox is isolated, and it can be safely discarded. It also explains the operations are evolution operations, providing useful behavioral context.

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 with no redundant content; front-loaded with the main action, then safety note. Every word earns its place.

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?

For a tool with 4 params and no output schema or annotations, the description covers the core purpose, optional operations, and safety. It also hints at the diff behavior. It lacks return-format details, but the mention of showing differences partially compensates.

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 the schema already documents all four parameters. The description adds that operations are evolution operations and mentions applying a hypothesis, but its phrasing '(list of evolution operations)' could be misread as defining the hypothesis parameter rather than operations, introducing ambiguity.

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 uses a specific verb ('Create') and resource ('isolated sandbox branch') and clarifies optional application of operations and diff display. This distinguishes it from sibling tools like create_branch by emphasizing isolation and safety.

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?

It states the sandbox is for testing a hypothesis and can be discarded if it fails, implying use for safe exploration. It does not explicitly name alternatives or exclusions, but the isolation context ('parent session never touched') provides clear usage context.

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