LFG Alarm

Search the LFG library

search_library

Read-onlyIdempotent

Searches LFG's own library. For LFG's own sounds and wallpapers; KLIPY GIFs and the person's own uploads are separate searches. sounds: over 500 songs, voices, tones and themes, each tagged with the moods it fits ("unhinged", "rise and shine", "panic", "calm bestie", "degen"), its energy and its voice; a category lists a whole shelf, and an empty search lists staff picks. looks: wallpapers by vibe, theme, mood, scene or colour: a theme's pictures ("christmas", "birthday", "love", "halloween"), drawn looks, and live wallpapers, moving backgrounds the phone draws, each with a mood and six colour sets ("calm", "rage", "cosmic", "ocean", "fire", "pink"). Returns up to 10 sounds, or up to six live wallpapers and, for each of up to three vibes, up to eight pictures and six drawn looks, each with the id an alarm takes. A search that matches no look lists the vibes and moods.

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": {
      "kind": "<kind>",
      "query": "<query>"
    },
    "name": "search_library"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes	sounds for the alarm's sound, looks for a wallpaper.
`query`	Yes	Moods, styles, scenes, colours or words, "unhinged", "sweet morning", "drill sergeant", "golf", "ocean, purple". Empty lists staff picks (sounds) or every vibe and mood (looks).
`voice`	No	Sounds only: no voice, spoken, sung or wordless.
`energy`	No	Sounds only: how loud.
`category`	No	Sounds only: one of the library's categories, as the app lists them, by id: "cinematic", "drill_sergeant", "your_bestie", "sirens", "chimes", or with its group where two share a name, "music/anime". Lists the whole category; query is not needed with it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 1, 2026

changedInput schema / properties / kind / description

Previous value: -"sounds for the alarm's sound, looks for a drawn wallpaper."New value: +"sounds for the alarm's sound, looks for a wallpaper."

changedInput schema / properties / query / description

Previous value: -"Moods, styles or words, \"unhinged\", \"sweet morning\", \"drill sergeant\", \"golf\". Empty lists staff picks (sounds) or every vibe (looks)."New value: +"Moods, styles, scenes, colours or words, \"unhinged\", \"sweet morning\", \"drill sergeant\", \"golf\", \"ocean, purple\". Empty lists staff picks (sounds) or every vibe and mood (looks)."

First observedOct 20, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behaviour: exact result caps (10 sounds; six live wallpapers; three vibes × eight pictures and six drawn looks) and the no-match fallback that returns vibes and moods instead of an empty list. That fallback is the kind of non-obvious behaviour an agent needs to interpret a result correctly.

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?

Purpose and the key exclusion are front-loaded, and every clause carries usable information about the taxonomy. It is still a dense run-on with long tag enumerations ("unhinged", "rise and shine"…) that partially duplicate the query parameter's examples, costing some scannability.

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 carries the full burden of explaining returns and does so concretely: counts per result type, what each item carries (id usable by an alarm), and the degenerate no-match case. Nothing essential for calling or interpreting this search is missing.

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 the baseline is 3, but the description adds domain meaning: a category "lists a whole shelf" and supersedes query, empty query means staff picks for sounds versus every vibe and mood for looks, and looks carry a mood plus six named colour sets. These are interpretive details the schema only partly conveys.

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 ("Searches LFG's own library") and immediately scopes it by declaring that KLIPY GIFs and personal uploads are separate searches. An agent can distinguish this from search_gifs, list_my_media and set_media without opening any schema.

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 routes between the two modes ("sounds for the alarm's sound, looks for a wallpaper") and excludes the neighbouring domains (GIFs, own uploads) as separate searches. It also explains the empty-query behaviour for both kinds. It stops short of naming the specific sibling tools to use instead, so the agent must infer that search_gifs handles the GIF case.

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

All LFG Alarm tools Inspect

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.