LFG Alarm

Set a lottery alarm

set_lottery_alarm

Sets an alarm for a Recreation.gov lottery from find_lottery: it rings as the lottery opens, as a last call before it closes (three hours before, or half an hour for a one-day lottery), or when the results come out. Waking up opens the lottery's page to apply or see the results. A moment already past returns an error. Returns the alarm and its link.

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": {
      "lottery_id": "<lottery_id>",
      "time_zone": "<time_zone>"
    },
    "name": "set_lottery_alarm"
  }
}

Input Schema

Name	Required	Description	Default
`note`	No	A note from the person about the alarm, in their words, shown under its trigger on the alarm's page and in the Daily drop. Up to 500 characters; an empty note clears it.
`vibe`	No	The feel of the alarm in a few words, and the kind of background and colour if the person named them: "fun poppy anime", "calm", "a simple bell", "hype for a token launch", "ocean waves, purple", "neon and chaotic". LFG picks a sound and a look from its library to match: a live, moving wallpaper when one fits, otherwise a drawn one. Wallpaper words given here replace the look's words; a colour given here makes it a plain gradient in that colour.
`reach`	No	Who can join: private (only the person), friends (people on its list, or with its link), public (anyone; listed in Discover).	private
`sound`	No	The shelf of our library closest to the sound they asked for, read for what they mean: lo-fi or study beats is music/chill, "make it a vibe" might be music/chill, music/rnb or music/beats, hype me up is voices/hype_man, yelling at me is voices/drill_sergeant. "own" for one of their own uploads ("my song"). "soundcloud" when they asked for SoundCloud, or no shelf is close: a genre we have no shelf for (k-pop, drum and bass), or an artist or a song by name; put what to look for in song_search, and they play SoundCloud songs and tap one. Leave it out when they said nothing about the sound. A song from Apple Music, or a song or voiceover made for them: leave this out, make the alarm, and say they get it in the alarm's Studio, under its sound, after Arm it. Never say you will make one. The wallpaper follows the song unless one is asked for.
`theme`	No	A theme or holiday: the alarm gets a song in its moods, a new alarm a title written for it, and a wallpaper dealt for it for variety, one of the theme's pictures, a GIF, a live wallpaper or a gradient. A vibe given as well shapes that ("cozy", "degen"); wallpaper words or a title given are kept. One of: birthday (Birthday), love (Love), night_out (Night out), shopping (Shopping), winter (Winter), christmas (Christmas), hanukkah (Hanukkah), diwali (Diwali), halloween (Halloween), thanksgiving (Thanksgiving), friendsgiving (Friendsgiving), new_years (New Year's Eve).
`title`	No	Short name for the alarm. When absent, the place and the moment, "The Wave lottery opens".
`moment`	No	When it rings: as it opens, a last call before it closes, or when results are out.	opens
`surprise`	No	For a friends alarm: keep it a surprise. People who join see a curtain instead of its title, picture, sound and note until it rings. Free on every plan.
`link_mode`	No	For a friends alarm, what its link does: open (anyone who opens the link rides along, the default) or approve (anyone else with the link asks first and the person says yes or no). Invited people walk straight in either way.
`time_zone`	Yes	The person's IANA time zone, "America/Los_Angeles".
`add_groups`	No	For a friends alarm: names of the person's friend groups whose members to let in, "Family". Members get a notification.
`add_people`	No	For a friends alarm: up to 20 people to let in, as usernames of the person's LFG friends or as email addresses. Friends get a notification; an email address with no LFG account gets an invitation. Any other username is refused.
`gif_search`	No	2 to 5 plain words to search GIFs with, written for this alarm, "solana pump celebration", "sleepy cat monday": used if the look dealt is a GIF, which has no words of its own. Fill it whenever you make an alarm.
`look_words`	No	Short words of your own for the wallpaper, written for this alarm, "SOL TO THE MOON", "EXAM DAY", "BEACH BY 6": used if the look dealt is a live wallpaper or a gradient, in place of its own words. 2 to 4 words. Unlike wallpaper_words, the look is still dealt. Fill it whenever you make an alarm.
`lottery_id`	Yes	The lottery_id from find_lottery.
`song_search`	No	With "soundcloud": what to look for there, in their words, "k-pop", "fred again".
`upload_name`	No	With "own": the name they gave the upload, "my dog picture". Left out, one of theirs is used.
`words_color`	No	Colour of the words as hex, any colour, "#D7FF00".
`hide_trigger`	No	Needed with surprise, true or false: whether to also keep back when and why it rings, so people who join only know that it will. A surprise is not made until it is given.
`snooze_times`	No	How many times it can be snoozed: 3, 10 or unlimited.
`silent_snooze`	No	true to snooze without the spoken roast LFG plays by default.
`snooze_minutes`	No	Minutes each snooze lasts: 5, 10, 15, 30 or 60.
`wallpaper_kind`	No	Only when they named a kind: a gradient, a live (moving) wallpaper, a gif or meme, or "own" for one of their own uploads ("my wallpaper", "the picture I uploaded"). Left out, LFG deals one of every kind in turn.
`wallpaper_color`	No	Wallpaper background colour as hex, any colour, "#5B2BFF".
`wallpaper_words`	No	Words drawn on the wallpaper, "WAKE UP"; a line break starts a new line. Up to 40 characters; it looks best as 1 to 4 short words, since the words are drawn as large as the square allows.
`people_confirmed`	No	Whether the person has confirmed the people and groups being added. Nobody is added or told without it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

addedInput schema / properties / gif_search

Added value: +{
+  "description": "2 to 5 plain words to search GIFs with, written for this alarm, \"solana pump celebration\", \"sleepy cat monday\": used if the look dealt is a GIF, which has no words of its own. Fill it whenever you make an alarm.",
+  "maxLength": 60,
+  "minLength": 2,
+  "type": "string"
+}

addedInput schema / properties / look_words

Added value: +{
+  "description": "Short words of your own for the wallpaper, written for this alarm, \"SOL TO THE MOON\", \"EXAM DAY\", \"BEACH BY 6\": used if the look dealt is a live wallpaper or a gradient, in place of its own words. 2 to 4 words. Unlike wallpaper_words, the look is still dealt. Fill it whenever you make an alarm.",
+  "maxLength": 40,
+  "minLength": 1,
+  "type": "string"
+}

AddedNov 10, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The annotations already establish that this is a non-read-only, non-destructive, open-world mutation. The description adds meaningful behavior beyond them: trigger timing, the special last-call rule, that waking opens the lottery page, the past-moment error, and that it returns the alarm and its link. It does not clarify idempotency or notification side effects, which keeps it from a 5.

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?

The description is four short sentences, front-loads the core action, and every sentence adds useful information about triggers, error behavior, or return value. There is no filler.

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 26-parameter tool with no output schema, the description covers the core purpose, trigger behavior, error condition, and return value adequately. It omits a high-level summary of social and customization capabilities, but those are exhaustively documented in the schema descriptions.

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 schema already carries most parameter meaning. The description still adds useful context by tying lottery_id to find_lottery and explaining the moment values with concrete last-call timing. It does not add meaning for the many customization parameters, but that is reasonable given the rich schema.

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?

The description states a specific verb and resource: it 'Sets an alarm for a Recreation.gov lottery from find_lottery.' That clearly distinguishes it from generic alarm siblings such as set_event_alarm or set_drop_alarm without needing the 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?

It gives clear usage context: the lottery must come from find_lottery, and the alarm can ring at opens, last_call, or results. It also states a when-not condition: 'A moment already past returns an error.' It does not explicitly name alternatives or say when to prefer this over other alarm tools, 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 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.