terminal_run_private

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

Adds substantial context beyond the annotations: output is suppressed, the finished event carries only exitCode/reason, a privateCommand capability is required with fail-closed behavior on older devices, and there is no credential argument at all. These are exactly the non-obvious traits an agent needs before invoking a destructive, open-world command.

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?

Six short sentences, front-loaded with the purpose and then the safety constraints; no filler. The telegraphic phrasing ("The ordinary shell is retained") is slightly clipped but still carries information.

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?

With no output schema, the description still explains what the completion signal contains (exitCode/reason) and the waiting protocol, which is the key completeness gap for this tool. It does not point at terminal_cancel_private_input for aborting an in-progress private input, a minor omission.

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%, so the description carries the burden; it does add real meaning for argv by mandating nonsecret arguments only. timeoutSeconds is left entirely to the schema (default 120, max 300), so the coverage gap is only partly closed.

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 a command that needs a password or other secret using the device Private Input form") and immediately scopes it against the ordinary shell path. An agent can tell this apart from terminal_input or terminal_cancel_private_input without reading any schema.

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?

Gives explicit when-to-use (secret-needing commands) and hard exclusions (never put a password/token in argv, terminal_input, chat or a file), plus the precondition of device-confirmed waiting_for_private_input. It does not name the sibling tools by name, so routing against terminal_input/terminal_cancel_private_input is implied rather than spelled out.

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