Skip to main content
Glama
Sign In

0bull Phone Farm

by net.0bull
OverviewDiscussionsAdmin

Phone Command Tool

phone-command-tool
Destructive

Send a device command to a farm phone. The phone must show video_live: true in list-phones-tool. Supported ops:

  • clipboard_set (text): set the phone clipboard

  • clipboard_get: read the phone clipboard back

  • open_url (url): open a URL / deep link

  • reboot: restart the phone (admins only; refused for everyone else)

  • clear_photos: empty the camera roll

  • get_ip: report the phone's LAN IP

  • brightness (level): set screen brightness (0-1)

  • wifi / airplane / cellular / flashlight (on): toggle the named radio/flashlight Op-specific fields (text, url, level, on) are only sent when provided. Returns a run id. The run succeeds once the phone has run the command; for get_ip and clipboard_get its result.value holds the IP or clipboard text.

Input Schema

NameRequiredDescriptionDefault
onNoDesired on/off state (for wifi, airplane, cellular, flashlight). Optional.
opYesCommand op: clipboard_set, clipboard_get, open_url, reboot, clear_photos, get_ip, brightness, wifi, airplane, cellular, flashlight.
urlNoURL or deep link to open (for open_url). Optional.
slotYesPhone slot to command, given as the `slot` UUID from list-phones-tool (its display name like "slot12" is not accepted). The phone must show `video_live: true` there.
textNoText to set on the clipboard (for clipboard_set). Optional.
levelNoBrightness level 0-1 (for brightness). Optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / level / maximum
      Added value: +1
    • addedInput schema / properties / level / minimum
      Added value: +0
    • addedInput schema / properties / op / enum
      Added value: +[
+  "clipboard_set",
+  "clipboard_get",
+  "open_url",
+  "reboot",
+  "clear_photos",
+  "get_ip",
+  "brightness",
+  "wifi",
+  "airplane",
+  "cellular",
+  "flashlight"
+]
    • changedInput schema / properties / slot / description
      Previous value: -"Phone slot to command, given as the `slot` UUID from list-phones (its display name like \"slot12\" is not accepted). Must be cast/live."New value: +"Phone slot to command, given as the `slot` UUID from list-phones-tool (its display name like \"slot12\" is not accepted). The phone must show `video_live: true` there."
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations flag destructive/openWorld but the description adds the concrete consequences: clear_photos empties the camera roll, reboot is permission-gated and refused otherwise, op-specific fields are only sent when provided, and the run model (returns a run id; success means the phone has executed it). Those are behavioral traits the annotations cannot express.

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?

Front-loaded with the action and the precondition, then a scannable op list. The op enumeration mildly duplicates the schema enum, but each line adds per-op meaning (admin gate, camera roll, LAN IP) that the enum alone does not carry.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly fills the gap by explaining the async run-id return model and that get_ip and clipboard_get surface their value in result.value. Combined with the preconditions, an agent has everything needed to call it and interpret the response.

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 100% so baseline is 3, but the description adds mapping semantics the schema only hints at — which field pairs with which op (text→clipboard_set, url→open_url, level→brightness, on→radio toggles) and the rule that unprovided fields are not sent.

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+resource ('Send a device command to a farm phone') and enumerates the exact supported operations, so an agent knows the capability precisely. It does not, however, differentiate from sibling tools like phone-control-tool, phone-snapshot-tool, or run-phone-agent-tool, which likely overlap in scope.

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?

Gives concrete preconditions (phone must show `video_live: true` in list-phones-tool, slot must be the UUID not the display name) and an explicit exclusion ('reboot: admins only; refused for everyone else'). It stops short of naming an alternative sibling when this tool is the wrong choice, so it falls short of a 5.

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

All 0bull Phone Farm toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources