write_sandbox_file

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

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses that files are overwritten without asking, parent directories are created, the network flag selects a specific sandbox, sandboxes do not share filesystems, and the call returns the path and byte count.

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 efficiently composed, with no filler. It front-loads the core purpose, then covers key usage details, behavioral caveats, and return information in a compact sequence.

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's moderate complexity and the presence of an output schema, the description is complete. It covers purpose, parameters, sandbox isolation semantics, overwrite behavior, and return value, leaving little ambiguity for an agent.

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 description coverage is 0%, so the description must compensate. It explains path should be absolute, provides an example, and clarifies the network flag's role in sandbox selection. Content is implied as the text to write but is not explicitly labeled, which prevents a perfect score.

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 clearly states the tool writes a text file inside the sandbox, creating parent directories as needed. It names specific use cases (script, fixture, input data) and distinguishes itself from sibling read/list tools by focusing on writing.

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 context for when to use the tool: to place files where sandboxed code can read them, with the same filesystem visible to run_python and run_command. It also explains the network flag selects which sandbox, but it does not explicitly name alternatives or state when not to use this tool.

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