terminal_input

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

Annotations mark the tool as destructive and non-idempotent, but the description adds substantial behavioral detail: paste normalization, modifier support, mouse reporting requirements, no-op focus, per-action mode checks, and the fact that settling errors do not undo input. This is exactly the kind of context an agent needs before sending input.

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 dense but perfectly structured: core contract first, then per-action semantics, an illustrative example, and failure/retry guidance. No sentence is filler, and the most important information is front-loaded.

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 complex input tool with no output schema, the description names the return fields, explains failure modes, gives a runnable example, and warns that a settling error does not undo input. Nothing essential for correct invocation appears to be missing.

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?

Since schema description coverage is 0%, the description carries the full burden, and it delivers: it explains what each action type does, the meaning of modifiers, why mouse actions need coordinates, what wait options exist, and the raw byte behavior. The example also clarifies the expected action array shape.

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?

Opens with a specific verb ('Send') and clear resource ('ordered batch of actions'), and names exactly what is returned: styled screen, actionsCompleted, and inputSent. The per-action detail makes it unmistakably distinct from sibling tools like terminal_snapshot or terminal_resize.

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?

Provides clear operational context for each action type, including when mouse actions fail, when focus is a no-op, and how modes are checked per action. It stops short of explicitly naming alternatives such as terminal_snapshot for read-only inspection, so it lacks a formal when-to-use versus alternative statement.

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