Skip to main content
Glama

hands_type

Clears and types text into a specified form field using its ref, label, placeholder, or name, while refusing password, OTP, and card fields so users enter sensitive data themselves.

Instructions

Clear and type into a field by ref (or unique label/placeholder/name). Refuses password/OTP/card fields — the user must type those.

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": {
      "field_ref": "<field_ref>",
      "text": "<text>"
    },
    "name": "hands_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
field_refYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden and does deliver one important trait: a hard refusal on sensitive fields (password/OTP/card), which tells the agent a call may fail by policy rather than by error. It omits failure modes, whether an existing value is replaced or appended (only implied by "clear"), and any focus/scroll requirements.

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 locator, with the safety constraint immediately after. No filler; the only mild weakness is that the locator forms are parenthetical and slightly compressed.

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?

For a simple two-parameter tool this covers the essential action, locator semantics, and the safety refusal. It still leaves the agent without knowledge of what a failed or refused call returns, or whether the tool implicitly focuses/scrolls the target field.

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 0%, so description must compensate. It does explain field_ref well, including the acceptable locator forms (ref or unique label/placeholder/name) and the uniqueness constraint. The text parameter is left entirely to its name, presumably the literal string to enter.

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 pair (clear and type) and target (a field), and names the accepted locator forms (ref, or unique label/placeholder/name), which an agent can map to the field_ref parameter. It does not differentiate itself from the sibling desktop_type, so the agent must guess between the two.

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 tool's scope (typing into a field) and there is an explicit exclusion: password/OTP/card fields are refused and must be typed by the user. However, there is no statement of when to prefer this over desktop_type or hands_press, and no prerequisites such as whether the field must already be visible or focused.

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