Updates the selected interaction target after cancelling current work at a barrier, letting you observe and replace the target without focusing or moving any window.
Cancel current work with a barrier, then observe and replace the selected target. Never focuses or moves a window.
| Name | Required | Description | Default |
|---|---|---|---|
| hwnd | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructive=true and non-idempotent, and the description adds real context: it cancels in-flight work via a 'barrier' and replaces the target while explicitly not focusing or moving a window. However, the definition of 'barrier', what exactly gets replaced, whether the cancellation is reversible, and any permission requirements remain unexplained for a destructive operation.
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?
Two short sentences with no filler, and the side-effect negation is placed last as a clear scope boundary. The text is efficient; the problem is missing content, not padding.
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 destructive, stateful tool involving cancellation barriers and target replacement, with no output schema and an undocumented parameter, the description is far too thin. An agent could not confidently predict what happens on invocation or how to supply hwnd correctly.
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?
There is one parameter (hwnd) with 0% schema description coverage, and the description never mentions it or explains the accepted format (a digit-only string matching ^[1-9][0-9]{0,19}$). 'Selected target' gestures at the parameter but does not establish what hwnd identifies or how a target becomes 'selected'.
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 verb phrase 'observe and replace the selected target' is obscure — neither 'target' nor 'replace' is defined in a domain sense, and the name already implies 'update'. The final negation ('Never focuses or moves a window') is the only part that clearly differentiates it from siblings like human_activate or human_mouse_move.
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?
'Cancel current work with a barrier' hints at a precondition, but there is no explicit statement of when to choose this over human_observe, human_activate, or human_mouse_click. No exclusions or alternatives are named beyond the single negative window claim.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.