Skip to main content
Glama

browser_keyboard

Read-onlyIdempotent

Keyboard at the focused element, beyond a whole press (browser.press_key): action 'down' / 'up' hold or release key (e.g. 'Shift', 'Control', 'a'; hold a modifier, press other keys, then release), 'insert_text' pastes text in one step without key events (fast, like a paste).

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": {
      "page_id": "<page_id>",
      "action": "<action>"
    },
    "name": "browser_keyboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNo
textNo
actionYes
page_idYes
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add operational detail, and it does: insert_text is disclosed as bypassing key events and behaving like a paste, which materially changes what the agent should expect from listeners and input masking. It does not say what happens on an unfocusable target or whether anything is returned, leaving a small gap.

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?

Everything is packed into one dense sentence with no filler, and the sibling contrast is embedded early. The parenthetical mid-sentence reference to browser.press_key interrupts the flow of the action list, which slightly hurts scannability for a tool whose main payload is three action values.

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?

With no output schema and 5 parameters, the description covers the mechanics that matter most: the action vocabulary, the key-vs-text split, and the modifier hold pattern. Missing pieces are minor for a browser-input tool, chiefly focus-failure behavior and the meaning of `page_id`, but nothing an agent needs to form a correct call is absent.

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 description coverage is only 20% and `action` has no enum in the schema, so the description carries real weight by enumerating the accepted values ('down', 'up', 'insert_text') and by tying `key` and `text` to specific actions with examples like 'Shift', 'Control', 'a'. It adds nothing about `page_id`, and `in_workspace` is covered only by the schema.

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?

The description names a concrete resource (keyboard input at the focused element) and a concrete capability set (down/up key holds and insert_text), then explicitly contrasts it with the sibling browser.press_key for a whole key press. An agent can distinguish this from browser_press_key and browser_fill without opening either schema.

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?

It routes the agent clearly: use browser.press_key for a complete press, use this tool for holding/releasing modifiers or for pasting text without key events. The modifier workflow ('hold a modifier, press other keys, then release') is spelled out as a usage pattern. It stops short of stating exclusions such as when the target is not focusable, so it is not a full 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.