run_command

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

With no annotations provided, the description carries the full burden of disclosing behavior. It only states the return values (stdout, stderr, exit code) but fails to mention that commands can have side effects within the sandbox, potential resource implications, or behavior on timeout. This is a significant gap for a command execution tool that could be destructive.

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 two short sentences, front-loaded with the core action and immediately followed by return value information. Every word earns its place; no fluff or repetition of schema details.

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 basic action and outputs but lacks context on prerequisites (e.g., an active sandbox), potential side effects, or error handling. Given the tool's complexity (arbitrary command execution) and lack of output schema/annotations, it is adequate but incomplete for an agent to fully understand the tool's safety and operational context.

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 100%, so the schema already fully documents all three parameters. The description adds no extra semantic meaning beyond what is in the schema; it doesn't explain nuances like the timeout range or how the sandbox_id is obtained. Baseline 3 is appropriate.

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 a specific action ('Execute a shell command') and its context ('inside a sandbox'), distinguishing it from sibling tools like create_sandbox and read_file. The verb + resource combination is precise and unambiguously identifies the tool's function.

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 implies usage by specifying 'inside a sandbox,' but does not explicitly state when to use this tool versus alternatives or provide exclusions. It also doesn't mention that the sandbox must already exist (though the schema hints at this via the sandbox_id description). No direct comparison with sibling tools is given.

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