Skip to main content
Glama

tab_type

Types text into a browser page field or focused canvas app using real keyboard input, optionally replacing content or submitting; get field refs from tab_read.

Instructions

Type into a text field of a page in the user's browser with the real mouse and keyboard, or without a ref into whatever has the focus (a canvas app editing text). With a ref the field is clicked to focus it, its content is replaced (or appended to with clear=false), and the text is typed, so the page reacts as it would to the user. With a ref it returns the value the field holds afterwards (hidden for passwords), or with submit what changed on screen; without one it always returns what changed on screen. Take the field's ref from tab_read. For several fields at once use tab_fill; for a native select dropdown use tab_select_option.

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": {
      "text": "<text>"
    },
    "name": "tab_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoElement ref: the number in brackets in tab_read output, e.g. 12 for "[12] button". Refs stay valid while the element stays on the page. Omit it to type into whatever already has the focus in the tab, such as the text a canvas app (a design tool) is editing after a double-click: nothing is clicked, cleared or checked then, so a line break goes as Shift+Enter whatever has the focus, and the result reports what changed on the page instead of the field's value.
textYesText to type. Any characters work: capitals, symbols, accents, emoji. A line break (\n) is typed as Shift+Enter, which starts a new line in a chat box or text area without sending; with a ref, a single-line field refuses line breaks.
clearNoSelect and delete what the field holds before typing. Defaults to true with a ref; without one nothing is cleared, and clear=true is refused.
tabIdNoTab id from tab_list or tab_read. Defaults to the active tab of the browser window the user used last.
submitNoPress Enter after typing, which usually submits the form. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that a ref causes a click-to-focus, that content is replaced or appended with clear=false, that passwords are masked in the returned value, and that submit changes the return payload to an on-screen diff. It stops short of describing failure modes (stale or missing ref, disabled or uneditable field) and any permission prerequisites, which leaves a gap for a mutation tool with zero annotation coverage.

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 mode split, then alternatives last, which matches how an agent reads. The middle section on return values is slightly dense and repeats 'what changed on screen' twice, costing a little crispness.

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

Completeness5/5

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

No output schema exists, and the description compensates by specifying exactly what is returned in each mode (field value, masked for passwords, or on-screen diff). Combined with the ref-sourcing pointer and alternative routing, an agent has enough to call this correctly on the first try.

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 already 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: clear is only refused without a ref, line breaks become Shift+Enter, and submit switches the return value from field value to screen diff. That coupling between ref and the other params is genuinely additive.

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 ('Type into a text field of a page in the user's browser with the real mouse and keyboard') and immediately defines two distinct modes (with ref vs. without ref into the focused element). It clearly separates itself from tab_fill (multi-field) and tab_select_option (native selects), so an agent can pick it without opening another 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 explicit routing: use tab_fill for several fields at once, tab_select_option for a native select dropdown, and take the ref from tab_read. It also states the exact condition for omitting ref (canvas app already editing text after a double-click), which is the non-obvious case an agent would otherwise get wrong.

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