tmux_send

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It adequately reveals that the tool may create sessions, that it never kills sessions, and that it uses C-c to stop old programs before sending new start commands. This addresses the main side effects and de-risks agent usage. It does not mention the effect of the 'enter' parameter, but the core behavior is well covered.

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 brief, front-loaded with the primary action, and then lists relevant reuse rules in a structured manner. Every sentence contributes substantive guidance with no filler or repetition.

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?

Given that an output schema exists, return values need not be described. The description covers the core call scenario, the missing-session edge case, and the operational constraints needed to execute correctly. Combined with the schema's parameter names, this is sufficient for an agent to invoke the tool safely.

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 must compensate. It explains 'session' and 'command' implicitly by their names and the tool's purpose, but never describes the 'enter' parameter, which is crucial because it determines whether a newline is sent after the command. This leaves a meaningful semantic gap.

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 states a specific verb and resource: 'send keys/command to the specified tmux session'. It also clarifies the behavior when the session does not exist. This clearly differentiates from sibling tools like tmux_status and tmux_capture, which are about inspecting state rather than sending input.

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 description provides clear behavioral usage rules: auto-creates a detached session when missing, never kill-session, and sends C-c before restarting a program. This gives the agent practical guidance on how to use the tool safely, though it does not explicitly contrast use cases with alternatives like exec_cmd or tmux_capture.

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