Skip to main content
Glama
Sign In
gwagent

gwagent

by vcnngr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

device_install_adb_keyboard

Installs the ADBKeyboard APK from a local file path onto an Android device or emulator, with confirm=true required for this action.

Instructions

Install ADBKeyboard (not needed: the on-phone server types any Unicode; the office phone forbids APK installs).

Requires confirm=true (outward-facing or destructive).

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": {
      "apk_path": "<apk_path>"
    },
    "name": "device_install_adb_keyboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoMust be true: this action is outward-facing or destructive.
apk_pathYesLocal path of ADBKeyboard.apk (github.com/senzhk/ADBKeyBoard).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden; it does disclose that the action is 'outward-facing or destructive' and requires confirm=true, plus the environment restriction on APK installs. It omits the concrete side effects an agent would want — whether the IME is enabled/switched, whether root or reboot is involved, and how to revert — so disclosure is partial.

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 with the caveat front-loaded before the mechanics. The compressed parenthetical is dense but every clause carries decision-relevant information; no 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?

For a two-parameter mutation with no output schema and no annotations, the description covers when to skip it and the confirm gate, but says nothing about post-install effects or verification. Adequate to decide whether to call, thin on what happens once you do.

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 description coverage is 100%, and both parameters are documented in-schema (apk_path's local path and source repo, confirm's required-true semantics). The description adds no parameter detail beyond restating the confirm requirement, so the baseline 3 applies.

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: 'Install ADBKeyboard' is concrete and distinct from the device_* siblings like device_push or device_shell. The parenthetical adds scope-limiting context (it's usually redundant), which further sharpens the purpose.

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?

Explicitly says when NOT to use it ('not needed: the on-phone server types any Unicode') and flags a policy blocker ('the office phone forbids APK installs'), which is exactly the kind of exclusion that prevents wasted calls. It stops short of naming the preferred sibling (e.g. ui_type) to use instead.

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

Deploy Server

Other Tools