Skip to main content
Glama

browser_press

browser_press

Simulate a key press with optional modifiers on a specific interactive element, letting agents trigger form submissions, shortcuts, or keyboard navigation in a browser tab.

Instructions

Press a key on an element returned by browser_get_interactives. Supports optional modifier keys.

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

Input Schema

NameRequiredDescriptionDefault
keyYes
tab_idYes
frame_idNoChrome frame ID inside the tab from browser_get_frames. 0 is the top document, which is the default.
modifiersNo
element_idYesOpaque element_id returned by browser_get_interactives.
session_idNoSession that owns the tab. Pass it on every call so the runtime can refuse a tab another session holds.
session_nameNoName for this conversation's Chrome tab group, so the tab bar reads as the task instead of a generated id. Sticky: pass it once when the name becomes clear, and again only to rename.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, so the safety profile is covered. Beyond that the description only says 'Supports optional modifier keys', which merely restates the existing modifiers array. It says nothing about focus requirements, whether the key dispatches to a focused element or the named element, what happens if the element is not interactable, or whether events are keydown/keyup/press.

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?

Two short sentences, front-loaded with the action and target, with zero filler. It is efficient, though the second sentence is close to redundant with the schema's modifiers field.

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

Completeness2/5

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

With 7 parameters, no output schema, and 57% description coverage, an agent still cannot tell what string to put in key or how session_id/self.session_name interact with the tab it already holds. For an input-heavy browser automation tool, the definition leaves too much to inference.

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

Parameters2/5

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

Schema description coverage is only 57%, and the description documents none of the undocumented parameters (tab_id, key format, modifiers semantics). Critically, key has only minLength 1 with no enum, so the accepted vocabulary ('Enter', 'a', 'ArrowLeft', etc.) is never explained anywhere. The mention of modifiers adds nothing beyond the schema's own enum.

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

Purpose4/5

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

States a specific verb and target ('Press a key on an element') and ties element_id provenance to the sibling tool browser_get_interactives, so the agent knows the prerequisite discovery call. It does not distinguish itself from near-neighbours like browser_type, which also sends keyboard input, so it stops 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.

Usage Guidelines3/5

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

Usage is implied by the phrase 'element returned by browser_get_interactives', which tells the agent when the element_id will exist. There is no explicit guidance on when to prefer this over browser_type (e.g. Enter/Escape/hotkeys vs. literal text) and no exclusions.

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