win_send_keys

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

The description adds behavioral details: background key posting, message-based (WM_KEYDOWN/UP), and unreliability for modifiers. Annotations don't cover these, so the description adds significant context. Lacks info on error handling for invalid handles.

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 concise: one-line purpose, args/returns summary, and a crucial caveat. No wasted words, and key 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?

Given the tool's complexity (4 parameters, output JSON), the description covers purpose, usage hints, and return format. The schema provides parameter details, and the description adds behavioral transparency, making it complete.

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 main description only mentions 'target window plus key names' for the params argument, adding little beyond the schema. However, the input schema provides detailed descriptions for each parameter, making the overall parameter semantics adequate.

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 tool posts key presses to a specific window without focusing it, using Win32 messages. This distinguishes it from sibling tools like `press_keys` (global) and `win_set_control_text` (text entry).

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 explicitly notes that modifier combos are unreliable for apps checking physical key state, and recommends `win_set_control_text` for text entry. This provides clear guidance on when to use alternatives.

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