Write to terminal

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

The annotations (all false) provide little behavioral context, so the description carries the burden. It does disclose the mechanism (writing to stdin), but it omits important behavioral details such as whether a trailing newline is needed to execute commands, whether the session must already exist, or any state-changing side effects beyond the write.

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 a single, front-loaded sentence with no filler. Every word contributes to the meaning, and it is appropriately sized for a simple two-parameter write operation.

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?

The tool is low-complexity and an output schema exists, so the core purpose is covered. Yet the description lacks critical usage context such as session prerequisites, newline behavior, or interaction with terminal_read/wait—details that would help an agent avoid common mistakes. Sibling names hint at the workflow but do not substitute for explicit guidance.

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%, but the description partially compensates by mapping 'keystrokes/commands' to the data parameter and 'terminal session' to session_id. It does not explain expected data format, encoding, or that session_id must reference an existing terminal session, leaving gaps that the schema also fails to fill.

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?

The description 'Send keystrokes/commands to a terminal session's stdin' clearly identifies the action (send) and the target (stdin of a terminal session). It is specific enough to be distinguished from siblings like terminal_read, terminal_resize, and terminal_signal, and the title 'Write to terminal' reinforces the purpose.

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?

The usage is implied by the phrase 'terminal session's stdin'—an agent can infer it is for writing to an existing interactive session. However, there is no explicit guidance about when to prefer this over alternatives like run_command or how it differs from terminal_signal or terminal_resize.

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