shell_exec

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

The description discloses several important behaviors beyond the annotations: ordered stdout+stderr capture, possible screenshot on error, and the critical fact that the VM remains locked until vm_unlock is called. This is meaningful context that the annotations do not provide, and it contradicts nothing.

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 concise sentences with no filler. The primary action and output behavior are front-loaded, and the VM lock warning is placed at the end where it serves as an important operational note.

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 lack of an output schema, the description provides a solid behavioral contract: ordered output capture, error screenshots, and VM lock lifecycle. It does not detail timeout/cwd defaults or exit-code semantics, but those are parameter-level details rather than major gaps in the tool's overall 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 only 20%, so the description needed to compensate for the undocumented parameters. It mentions captured output and screenshot-on-error, but it does not explain cwd, timeout_ms, or the screenshot_on_error parameter directly, and command semantics are only implicit in 'Run a command'. Most parameters are left to be inferred from their names.

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 states a specific action ('Run a command to completion') and a clear resource (a command on a VM), and it specifies behavioral details: captured ordered stdout+stderr and possible screenshots on error. This distinguishes it from interactive shell tools like shell_start and shell_read by emphasizing one-shot execution to completion.

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 clearly communicates the execution model: run to completion, capture output, and handle the VM lock by calling vm_unlock when finished. It does not explicitly name alternatives or exclusion criteria, but the 'to completion' wording provides enough context to separate it from interactive or streaming shell commands.

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