Skip to main content
Glama

Press a key

browser_press
Destructive

Press a key or shortcut on the focused browser element to close dialogs, pick suggestions, or submit forms. Click a field first; use text input tools instead for typing.

Instructions

Press a key or shortcut on whatever has focus (no ref; browser_click a field first). E.g. Escape closes a dialog, ArrowDown then Enter picks a suggestion; Enter may submit a form; reload keys are refused. For text, browser_type. Returns what changed.

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": {
      "key": "<key>"
    },
    "name": "browser_press"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesKey or +-joined shortcut, e.g. "Enter", "Escape", "Tab", "ArrowDown", "Control+a"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • changedInput schema / properties / key / description
      Previous value: -"e.g. \"Enter\", \"Escape\", \"Tab\", \"ArrowDown\", \"Control+a\""New value: +"Key or +-joined shortcut, e.g. \"Enter\", \"Escape\", \"Tab\", \"ArrowDown\", \"Control+a\""
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds real value on top by warning that Enter may submit a form (a side effect worth knowing), noting the reload-key guardrail, and promising a report of what changed. It stops short of describing navigation/focus side effects in general terms, but the safety-relevant behavior is largely disclosed.

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 core action and the focus constraint, then the alternatives and behavior notes; every clause carries information. The telegraphic fragments ('For text, browser_type.', 'Returns what changed.') are efficient but slightly clipped, and 'what changed' is a bit vague.

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?

For a single-parameter, destructive, open-world input tool with no output schema, the description covers prerequisites, side effects, guardrails, and an alternative tool. The only real gap is the vagueness of 'returns what changed', which matters somewhat since no output schema exists to define the return shape.

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% and the key format ('+-joined shortcut', examples) is already documented in the schema, so a 3 would be the floor. The description adds value by showing that multi-step key sequences are performed as separate calls ('ArrowDown then Enter'), which is semantics the schema alone does not convey.

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 (press) and resource (a key or shortcut) plus the crucial scoping detail that it applies to whatever currently has focus, with no element ref. It explicitly routes text entry to browser_type, so an agent can distinguish it from browser_type and browser_click without opening any schema.

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

Usage Guidelines5/5

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

Gives concrete when-to-use cases (Escape for dialogs, ArrowDown then Enter for suggestions), a prerequisite (browser_click a field first since there is no ref), an explicit alternative (browser_type for text), and an exclusion (reload keys are refused). Alternatives and conditions are named rather than inferred.

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