Trigger keyboard shortcuts and key combinations in real Chrome using modifiers like Ctrl, Shift, Alt, or Meta, enabling automation of copy, paste, and navigation without screenshots or CDP.
Press key(s) with modifiers: press_key("c",["ctrl"]) = Ctrl+C, press_key("Tab",["shift"]) = Shift+Tab.…
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| ref | No | ||
| frameId | No | frameId (omit=top) | |
| modifiers | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses the core action and modifier syntax, but omits context about event target (page vs OS), focus requirements, key release behavior, or side effects, which matters for an automation tool.
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 a single sentence with two illustrative examples; it is front-loaded with the action and parameter syntax, and every word earns its place. The ellipsis suggests the original may continue, but as provided it is appropriately sized and clear.
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?
With no annotations and no output schema, and four parameters (one undocumented), the description is too thin. It doesn't explain ref, doesn't give usage boundaries, and doesn't state what result or state change to expect, so an agent lacks some context needed for confident invocation.
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 description coverage is only 25%, so the description must compensate. It does explain key and modifiers via example calls, giving meaningful semantics to those parameters, but leaves ref entirely undocumented and relies on the schema for frameId. This partial compensation is adequate but incomplete.
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 ('Press') and resource ('key(s)') and provides concrete examples (Ctrl+C, Shift+Tab) that make the operation unmistakable. It clearly distinguishes itself from sibling input tools like type_text and click through the notion of pressing key combinations.
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?
No explicit when-to-use or alternative guidance is given. The examples imply keyboard shortcut usage, but there is no mention of when press_key should be preferred over type_text or other input tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.