send_keys

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

With no annotations, the description carries the full burden of behavioral disclosure. It adds useful behavioral details: keys are sent in order, and `esc` represents Escape. It does not explain what happens on invalid pane ids, whether key presses are delivered to a focused session, or the success/failure behavior, but the core behavior is transparent enough for a simple input tool.

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 short, focused, and front-loads the purpose while providing only the essential supplementary usage details. Every sentence earns its place with no redundancy or fluff.

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 tool with only two required parameters and an output schema already present, the description is mostly complete for calling the tool. It covers the main user needs: what it does, how to specify the target pane, and how to express keys. The main remaining gap is not mentioning how this differs from send_text or run_command beyond the explicit 'key presses' wording.

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 input schema provides only names and types, so the description must compensate and does so well. It clarifies the expected pane format with `w17:p1`, provides key examples, and clarifies ordering and the representation of Escape. Missing details are the expansion of key syntax or possible key names, but the examples give sufficient grounding.

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 clearly states the action and target: send key presses to a pane, with concrete examples such as ["enter"], ["esc"], ["ctrl-c"]. It is distinct from siblings like send_text or run_command because it specifically covers keyboard keys rather than text or command execution, though it does not explicitly name those alternatives.

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 includes practical guidance on how to specify pane ids and that keys are sent in order. However, it does not explicitly state when to prefer this tool over alternatives such as send_text or run_command, leaving the selection criteria implicit.

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