ui_send_keys

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

Discloses fallback behavior: tries cached coordinates first, then pywinauto element search. Also explains key syntax modifiers in detail. Adds value beyond sparse annotations (only openWorldHint). Missing: side effects on window focus, waiting behavior.

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?

Well-structured with sections and front-loaded note, but the key syntax section is extensive and could be condensed. Overall adequate but verbose.

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 6 parameters, no output schema, and low schema coverage, the description is incomplete. It covers 'keys' well but ignores other parameters, return value, error conditions, and prerequisites. Sibling tools exist but no explicit differentiation.

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?

Only the 'keys' parameter is described in depth with syntax examples. The other 5 parameters (automation_id, name, control_type, root_id, xpath) are merely listed without explanation. Schema has 0% description coverage, so the description carries full burden but fails to add meaning for most parameters.

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 'Send keyboard input to a UI element' and explains the fallback mechanism and key syntax. It does not differentiate from sibling tools like ui_send_keys_focused, but the purpose is specific and actionable.

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?

Includes a crucial 'Note' about resuming execution if app is at breakpoint, providing clear when-not-to-use guidance. Does not explicitly compare to alternatives like ui_send_keys_batch, but the context is helpful.

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