win_send_keys

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

Provides useful context beyond annotations by explaining it does not focus the window and uses Win32 messages. However, it does not disclose potential failure modes, side effects, or reliability limitations (those are in schema notes). Annotations indicate a mutation but not destructive, which is consistent.

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 and front-loaded with the essential behavior. Including args/returns format adds structure without bloat. Every sentence contributes meaning.

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 description is adequate for a simple tool with a rich input schema and output schema. It explains the core functionality and return type, though it omits edge-case handling like multiple window matches or invalid handles, which is somewhat covered by the schema's descriptive fields.

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 description only gives a high-level summary ('target window plus key names') and does not add detail per parameter. The input schema itself provides thorough descriptions for hwnd, keys, display, and window_title, so baseline 3 is appropriate.

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 uses a specific verb and resource: 'Post key presses to a specific window WITHOUT focusing it (Win32 messages).' This clearly distinguishes it from sibling tools like press_keys or win_set_control_text and states the mechanism.

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 implies a use case (sending keys to a background window without focusing) but does not explicitly state when to use this over alternatives or mention exclusions. The schema's note about preferring win_set_control_text is not part of the tool description itself.

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