guest_exec

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

Adds real context beyond the annotations: credentials come only from the server environment (no per-call auth params), and a host-side timeout may leave the guest command still running — a genuine hazard the annotations don't express. The destructiveHint is not explained in terms of what arbitrary PowerShell could do, which is the remaining gap.

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?

Four tight sentences, front-loaded with the mechanism, then auth, then return values, then the timeout caveat. The return-value sentence is partly redundant with the output schema but is short enough not to hurt.

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?

Output schema covers returns and annotations cover the safety profile, so the description is close to sufficient. It still leaves undocumented parameters and no explanation of the destructive flag's practical implications for a tool that executes arbitrary code.

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 coverage is 0% and the description never mentions vm_name or command — no naming convention for the VM, no shell/quoting syntax, no size limits on the command string. With two opaque parameters, the description should compensate and 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?

States a specific verb and resource: run PowerShell inside a guest VM via PowerShell Direct. That clearly separates it from the console_type_text/serial_send siblings, though it never names those alternatives explicitly.

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?

There is no guidance on when to use this versus guest_read_file, guest_write_file, guest_processes, or the console keystroke tools. An agent has to infer that this is the generic arbitrary-command escape hatch.

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