terminal_input

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

Annotations already flag destructiveHint=true, openWorldHint=true and non-idempotence, and the description adds value beyond them: a human-consent gating requirement and the fact that screenshots are returned automatically. It still doesn't disclose failure behavior when input control is not granted, nor whether data is submitted raw or executed.

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?

Two short sentences, the gating precondition front-loaded, and the response behavior second. No filler; each sentence carries distinct 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?

For a destructive, non-idempotent tool with no output schema, it covers the consent prerequisite and the automatic screenshot return, which is genuinely useful. However, the undefined payload format and unstated behavior when consent is missing leave the agent guessing on the two things that most affect a correct call.

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 single 'data' parameter is undocumented in both schema and description. The agent cannot tell whether data is raw keystrokes, a full command line, or whether a trailing newline is needed to execute it — a meaningful gap for the only input this tool accepts.

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+resource ('Send shell input'), which cleanly distinguishes it from read-oriented siblings like terminal_events and terminal_connect. It doesn't name an alternative tool explicitly, but the write/input framing makes the role unambiguous.

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?

Given a clear precondition: 'only while the human has granted AI input control,' which tells the agent when invocation is legitimate. It stops short of naming alternatives (e.g., terminal_events for reading output) or stating what happens if the grant is absent.

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