Skip to main content
Glama

desktop_type

Type text into a named field of a native Windows window so agents can fill forms and inputs. Refuses password-like fields so the user enters credentials.

Instructions

Type into a field of a native Windows window, by its visible name.

Password-like fields are refused - the user types those. Needs the desktop_control permission (default: ask).

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": {
      "title": "<title>",
      "control": "<control>",
      "text": "<text>"
    },
    "name": "desktop_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
titleYes
controlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden. It does disclose two meaningful traits: password-like fields are refused, and a desktop_control permission gate with default 'ask' applies — real context an agent would otherwise lack. It omits other important behavior for a mutation tool: whether existing text is replaced or appended, whether the field is focused/verified first, and what happens when the control name is not found.

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 scope, followed by the two safety constraints. No filler; the only loss is that the second sentence packs permission and refusal together rather than separating them.

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?

Given a simple three-string mutation tool with no output schema and no annotations, the definition covers the essentials: what it types into, how the target is identified, and the two refusal/permission behaviors. The remaining gap is parameter disambiguation between 'title' and 'control', which matters because both are required and undocumented.

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 description coverage is 0% for all three required parameters, so the description must compensate, and it partially does: 'by its visible name' explains that the control is addressed by visible label rather than an ID, and 'Type into a field' implies the text parameter. However, it never disambiguates 'title' (window title vs. field name) from 'control', leaving a genuine ambiguity between two required string parameters.

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 resource ('Type into a field') and scopes it to 'a native Windows window', which separates it from browser-oriented or generic typing siblings. It stops short of naming an alternative (e.g. hands_type) or clarifying the difference, so it is clear but not fully differentiated.

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?

The description implies usage (type into a Windows field identified by visible name) and gives two useful operating constraints: password-like fields are refused and the desktop_control permission is required with a default of 'ask'. It never says when to prefer this over desktop_click, hands_type, or desktop_read_value, so routing guidance is only implied.

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