Skip to main content
Glama

owa_press_key

Sends a keyboard shortcut such as F5 or Ctrl+S to the app window, optionally focusing a named control first. Refuses keys or dialogs that cannot be undone safely.

Instructions

Press a keyboard shortcut in the app window: "F5", "Ctrl+S", "Escape", "ArrowRight", "Space", "Shift+Enter". With find, that control is focused first -- arrow keys and Space belong to the panel that has focus (a slide list, a run player). Refuses a key whose control cannot be undone (F6 is Clear All), any key while the app is asking the user a question, and Enter or Space on such a control. F5 shows the projector and F10 clears every foreground extra: only when asked. The answer says what it brought up or moved; unverified means check before saying so.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "keys": "<keys>"
    },
    "name": "owa_press_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
findNoA control to focus first, by its label
keysYesThe shortcut as written on a tooltip, "Ctrl+Shift+A"
pageNoPart of the window URL, e.g. "reader.html"; default the main window.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.11.15

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the whole burden and does so well: refusal rules (non-undoable controls, dialog pending, Enter/Space on question controls), focus-dependent key semantics, and side effects of F5 and F10. It also flags the `unverified` result flag. It omits any permission or rate/state requirements beyond the pending-question case.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and examples, then progressively adds constraints. Dense but mostly load-bearing; the em-dash clauses and the F5/F10 aside are packed tightly enough that a quick read could miss a refusal rule, but nothing is truly redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A mutation-ish input tool with no output schema, so the description rightly explains the result signal ('what it brought up or moved', `unverified`). Refusal and side-effect behavior are covered. Minor gaps: nothing about what happens on an unrecognized key string or how `page` resolution fails.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description earns a step up by explaining what `find` actually does — focuses that control first and reassigns arrow/Space ownership to the focused panel (slide list, run player). `keys` is clarified as 'the shortcut as written on a tooltip'. Only `page` gets no extra narrative.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — press a keyboard shortcut in the app window — and immediately grounds it with concrete key examples ("Ctrl+S", "Escape", "ArrowRight"). It is clearly distinct from mouse-driving siblings like owa_click or owa_drag.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real conditional guidance: use `find` to focus a control first, and invoke F5/F10 side effects 'only when asked.' It also states when the tool will refuse. It stops short of naming a sibling alternative (e.g. click vs. key) for reaching the same control, so it is clear context rather than full when/when-not routing.

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