Skip to main content
Glama

Type into element

browser_type
Destructive

Type into a text field, textarea, or contenteditable from the latest observation. A non-editable element (editable: false, such as a submit button) returns ELEMENT_NOT_INTERACTABLE and does not change the page. length is the number of Unicode code points. A number, date, time, week, month, or color input that cannot hold the text returns INVALID_INPUT_VALUE and does not set the value. The typed value is not stored in the audit log. Events are not isTrusted; Browse Bridge does not spoof that flag. On a sensitive site, type returns APPROVAL_REQUIRED with approvalId. After Deny, the next type returns APPROVAL_DENIED with that approvalId once, even when the new observation has a new element id. Typed text is not part of that match. A later type may ask again. After Approve, the completed success includes that same approvalId and approved: true. A type that did not need approval does not include approvalId. Password fields return HUMAN_INPUT_REQUIRED — the human types that value; there is no Approve that types a password.

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": {
      "sessionId": "<sessionId>",
      "observationId": "<observationId>",
      "elementId": "<elementId>",
      "text": "<text>"
    },
    "name": "browser_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
submitNo
elementIdYes
sessionIdYes
observationIdYes
idempotencyKeyNoA key replays the original result only within ~60 seconds of the first call, only for the same Mcp-Session-Id, the same credential (API key or OAuth token), the same browser session, and the same tool. After the window, or under a different session/credential/tool, the call executes and bills normally. Reusing a key with different arguments returns IDEMPOTENCY_KEY_REUSED and is not executed or billed. Refusals (e.g. NO_HISTORY_ENTRY) are not cached, so the same key re-executes once state changes. A key passed in _meta is ignored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Adds substantial behavioral detail beyond the annotations: ELEMENT_NOT_INTERACTABLE and INVALID_INPUT_VALUE conditions, audit-log behavior, isTrusted handling, approval flows, denied-approval behavior, and password fields requiring human input. This is unusually rich transparency for a mutation tool.

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?

The core action is front-loaded, and most sentences carry distinct behavioral information. It is long but largely justified by the tool's complexity; some approval-flow details could be tightened, but there is little pure filler.

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

Completeness3/5

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

The description is thorough on error and approval edge cases, but it omits the submit flag's behavior and does not describe the normal successful return shape. Since there is no output schema and parameter coverage is low, these gaps leave the definition incomplete for safe invocation.

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 17%. The description explains text semantics such as Unicode code point length and password behavior, but it does not explain the optional submit parameter at all, nor does it clarify sessionId or observationId beyond the phrase 'latest observation.' With a critical mutation parameter like submit undocumented, the description does not compensate for the low schema coverage.

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 set: 'Type into a text field, textarea, or contenteditable from the latest observation.' This clearly distinguishes it from browser_click, browser_select, and browser_press_key without needing to name them.

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 clear context for when to use it: editable elements from the latest observation. It also explains that non-editable elements return ELEMENT_NOT_INTERACTABLE, implying a boundary. However, it does not explicitly say when to use alternatives such as browser_press_key or browser_select.

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.