bash_exec

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

With no annotations provided, the description carries the full burden and discloses key behaviors: writes go to an in-memory overlay and do not touch the real filesystem unless committed, and network is disabled unless JUST_BASH_NETWORK_ALLOW is set. This goes beyond a simple 'executes bash' and informs the agent about side effects and limitations.

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?

Three sentences efficiently convey the core purpose, sandboxing behavior, network conditions, and supported tools. The list of supported commands is long but necessary for capability discovery, and the description is front-loaded with the primary action.

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 bash execution tool with no output schema, the description covers critical behavioral constraints: sandboxed filesystem, network restriction, available commands, and optional runtimes. It omits return value format and commit mechanism, but given the complexity, the description is reasonably complete without being exhaustive.

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% for both parameters (script and timeout), so the baseline is 3. The description does not add specific parameter semantics beyond the schema, but it does contextualize the execution environment, which indirectly supports understanding of the script parameter.

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 'Execute a bash script in a sandboxed virtual filesystem mounted at the project root' – a specific verb, resource, and environment. It distinguishes from siblings like sandbox_status and sandbox_reset, which deal with sandbox state rather than execution.

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?

Provides clear context about the sandbox environment, network restrictions, and supported commands, implying when to use it for isolated bash tasks. Does not explicitly name alternatives or state exclusions, but the environmental guidance is sufficient for a single-purpose tool.

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