Press keyboard shortcuts or space-separated key sequences to control the Cascadeur UI, optionally targeting a specific window and waiting for UI updates.
Press keys or shortcuts, space-separated combos, e.g. 'ctrl+s', 'Escape', 'ctrl+a Delete', 'F'.
| Name | Required | Description | Default |
|---|---|---|---|
| keys | Yes | ||
| window | No | Window index or title substring (default: focused/main window). | |
| settle_ms | No | Milliseconds to wait for the UI to update before returning (default 150). |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It conveys input syntax but not where the keystrokes go, whether window focus changes, whether arbitrary/destructive sequences (the 'ctrl+a Delete' example implies they are possible) have side effects, or what is returned; the tool's degree of control over the OS/UI is never disclosed.
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?
A single front-loaded sentence with three illustrative examples, each earning its place by teaching the combo syntax. Nothing is wasted, though it is a sentence fragment and omits any hint of targeting behavior.
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 simple three-parameter input tool with no annotations or output schema, the description covers the essential calling convention but leaves the agent guessing about focus targeting, side effects, and what the call returns or confirms.
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?
Schema coverage is 67% and the undocumented parameter is 'keys' itself; the description compensates by explaining that combos are space-separated and giving literal example strings, which the schema does not. The other two parameters (window, settle_ms) are already documented in the schema, so no further detail is needed.
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 states a specific verb and resource ('Press keys or shortcuts') and illustrates the exact input syntax with three concrete examples, so an agent knows precisely what the tool does. It does not explicitly distinguish itself from siblings like ui_type or ui_click, which keeps it short of a 5.
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?
Usage is only implied: the examples ('ctrl+s', 'Escape', 'ctrl+a Delete') suggest when keystroke input is appropriate, but there is no statement of when to prefer this over ui_type, ui_click, or ui_invoke, and no prerequisites or exclusions are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.