exec_in_vm

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

With no annotations, the description must carry the behavioral disclosure burden. It explains the basic operation (SSH execution, combined stdout/stderr) but omits details about authentication, state changes, error handling, or the fact that the command runs with default permissions. More transparency would be beneficial.

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 a single sentence that immediately conveys the tool's purpose, followed by a crucial limitation. No unnecessary words; it is front-loaded and efficient.

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 is functionally complete for a basic understanding but lacks contextual details such as the requirement that the VM must be running, the return format (though output schema exists), and potential failure modes. Given the tool's complexity, this is adequate but not thorough.

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% and the description adds no parameter information. It does not explain what 'os' or 'command' entail, nor the purpose of 'release' or 'timeout_sec'. The description should compensate for the missing schema descriptions, but it does not.

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 action: 'Execute a shell command over SSH inside a running VM and return the combined stdout/stderr.' It distinguishes from sibling tools like list_supported_os, start_vm, console_output, etc., and includes a notable exception (plan9).

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 explicitly notes that the tool is not available for plan9 (no SSH), providing a clear when-not-to-use. However, it does not elaborate on when to use this tool over alternatives like console_output or mention prerequisites such as requiring the VM to be running.

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