terminal_input

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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, so the risk profile is known. The description adds non-obvious behavior beyond that: it is gated on human authorization, it must never carry secrets, and the response automatically includes shared screenshots. It stops short of describing what terminal state the input can affect or how errors surface, so it falls just short of a 5.

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?

Front-loaded with the primary purpose and the controlling precondition; the credential warning and the screenshot note each carry real information. Sentences are multi-clause and dense, but no sentence is filler.

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 one-parameter destructive tool with no output schema, the description covers gating, the secret-handling boundary, the sibling alternative, and the return payload (screenshots). What remains missing is the shape/semantics of the input payload itself.

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?

The single 'data' parameter has 0% schema description coverage, so the description must compensate. 'Shell input' implies raw input text, but it never says whether newlines/Enter must be included, whether it is a keystroke sequence or a whole command line, or how it is truncated. Adequate inference, no more.

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 (send shell input) plus the governing precondition (human-granted AI input control). It explicitly distinguishes itself from terminal_run_private, which handles the credentialed case, so an agent can route between the two without opening either 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 when-to-use (only under granted AI input control), an explicit exclusion (never passwords/tokens), and the named alternative for the excluded case (terminal_run_private with device-confirmed Private Input). Nothing about selection is left to inference.

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