Sends a remote key press to an LG webOS TV over the LAN and optionally captures the screen, so agents can navigate menus and observe changes when focused control is unknown.
Bounded remote key; foreground state cannot identify focused control. Observe unknown navigation visually.
| Name | Required | Description | Default |
|---|---|---|---|
| button | Yes | ||
| capture | No | auto |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose one real behavioral caveat — foreground state cannot identify the focused control, so navigation must be verified visually — but says nothing about side effects, key queuing, or what 'bounded' means operationally.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is short (two fragments of ~14 words), but the brevity is under-specification, not conciseness — the telegraphic phrasing conveys little usable information. It is front-loaded, though that content is cryptic.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need not be explained, but for a two-parameter mutating tool with no annotations and 0% schema coverage the description is far too thin. The meaning of 'bounded' and the capture parameter are never resolved.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description does not explain either parameter. 'Remote key' loosely gestures at the button enum, but the capture parameter (auto/never/always) is entirely unexplained despite having a meaningful behavioral effect.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The phrase 'Bounded remote key' is a verbless fragment that only hints at sending a remote key press, and the rest of the description is about verification rather than what the tool does. It distinguishes weakly from siblings like tv_click or tv_move, but never states the action+resource directly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Observe unknown navigation visually' hints that results must be confirmed with an observation tool, but explicit when-to-use/when-not and routing to alternatives (e.g., tv_click vs tv_press) are absent. Only a fragment of guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.