Skip to main content
Glama
mcp-server-shieldtv
by SDNick484

Press a remote key

shield_send_key

Press remote-control keys such as DPAD, CENTER, BACK, HOME, media, and volume on an NVIDIA Shield TV to navigate Android TV menus and controls, optionally repeating a key up to 10 times.

Instructions

Press a remote-control key on the Shield, e.g. DPAD_DOWN with repeat=3 to move down three rows.

<use_case> Navigate Android TV interfaces, menus, and controls using directional pad, enter, back, and home. </use_case>

<important_notes>

  • Only sends allowed key enum values; power toggles and raw text typing are not supported. </important_notes>

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": {
      "key": "<key>"
    },
    "name": "shield_send_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYes
repeatNoHow many times to press the key (1-10).

Output Schema

NameRequiredDescriptionDefault
sentYes
detailYes
shieldYes
outcomeYes
warningsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive. The description adds real value on top: it constrains input to allowed key enum values, rules out power toggling and text typing, and the repeat example discloses the repeated-press behavior that explains why the call is not idempotent. No rate limits or connectivity prerequisites are mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short structured blocks with zero filler: the headline sentence, the use case, and the constraint notes. The illustrative example is doing real work rather than padding.

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?

For a two-parameter tool with an output schema and informative annotations, this covers purpose, context, and key constraints. The only material gap is whether a target device/session must be active before pressing keys, which an agent might reasonably wonder about.

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 50% — the repeat parameter is self-documenting but the key enum is not. The description compensates by explaining repeat through example (repeat=3 moves three rows) and by characterizing the key space as directional pad, enter, back, and home plus media/volume keys. It does not enumerate every enum value, but the schema does.

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 ('Press a remote-control key on the Shield') and immediately grounds it with a concrete example ('DPAD_DOWN with repeat=3 to move down three rows'). The behavior is clearly distinct from siblings like shield_set_power and shield_launch_app.

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?

The <use_case> block names the context (navigating Android TV interfaces, menus, controls) and <important_notes> gives explicit exclusions — no power toggles, no raw text typing. It stops short of naming the alternative tool for those excluded operations (e.g. shield_set_power), so the routing is implied rather than explicit.

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