Skip to main content
Glama

Type

browser_type
Destructive

Replaces the full text of an input, textarea, or editable element by ref without appending. Use it to fill forms or search boxes, with an option to press Enter and submit.

Instructions

Replace the text of an input, textarea or editable element by ref (never appends). In an autocomplete box the result shows its suggestions: browser_click one. For a , browser_select. 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": {
      "ref": "<ref>",
      "text": "<text>"
    },
    "name": "browser_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYesFrom the latest snapshot, e.g. "e12" or "f1e3"
textYesFull new text ("" empties it); dates as YYYY-MM-DD
submitNoPress Enter after, e.g. to search or send

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / submit / description
      Previous value: -"Press Enter afterwards"New value: +"Press Enter after, e.g. to search or send"
    • addedInput schema / properties / text / description
      Added value: +"Full new text (\"\" empties it); dates as YYYY-MM-DD"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds the concrete meaning — text is replaced, never appended — plus the fact that it returns what changed and that autocomplete results require a follow-up click. It doesn't say what happens to caret/selection state or what a failure looks like, but it meaningfully extends the safety profile rather than restating it.

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

Conciseness5/5

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

Three short sentences, no filler, and the most important fact (replace, not append) is front-loaded. Every clause carries either a constraint or a routing hint.

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 destructive three-parameter mutation with no output schema, it covers the overwrite semantics, the return value ("what changed"), and the two follow-up paths an agent is most likely to need. Minor omission: no note on what happens if the ref is stale or the element isn't editable.

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

Parameters3/5

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

Schema coverage is 100% and the schema already explains ref format, the empty-string case, date format, and the submit flag. The description adds only the general "by ref" framing and an implied use of submit via the autocomplete example, so it sits at the baseline for fully documented parameters.

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?

Names a specific verb and resource ("Replace the text of an input, textarea or editable element by ref") and adds a decisive constraint ("never appends") that separates it from any append-style entry. It also explicitly routes <select> work to browser_select, so the agent can distinguish it from a sibling without opening schemas.

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 explicit when-to-use guidance for the two ambiguous cases: an autocomplete box (type, then browser_click a suggestion) and a <select> (use browser_select instead). It lacks a general exclusion statement against other siblings like browser_press or browser_actions, but the named alternatives cover the realistic confusion points.

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