Skip to main content
Glama

Create a Fun Friday custom pack

funfriday_create_pack

Create a custom content pack for the user's Fun Friday team, so the team plays their own material: Trivia Blitz questions (pack_type "trivia"), Imposter word lists (pack_type "faker") or Emoji Story phrases (pack_type "emoji_story"). A custom pack replaces the game's built-in content with the team's own — in-jokes, company trivia, a theme for the week. Only these three games take custom packs; for any other game, say so rather than calling this. Send the content in the one list that matches pack_type (for Imposter, either words or word_groups), and write it to play well (see each list's description). The host picks the pack in the lobby before pressing Start. Custom packs need a Pro or Business plan, which caps how many a team can keep — call funfriday_get_team first if unsure.

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": {
      "pack_type": "<pack_type>",
      "name": "<name>"
    },
    "name": "funfriday_create_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe pack's name as the team will see it in the lobby, e.g. "Office trivia". Up to 60 characters.
wordsNoFor pack_type "faker" only, when every word belongs to ONE theme: 2–500 related words or short phrases (up to 100 characters each). Each round pairs any two of them — one for the group, a near miss for the imposter — so they must all be the same kind of thing. Pick words close enough that the imposter can bluff (e.g. "latte", "espresso", "cappuccino"), not opposites or unrelated words. Ten or more gives variety across rounds. If the pack covers more than one theme, send word_groups instead.
phrasesNoFor pack_type "emoji_story" only: 1–500 phrases for players to tell in emoji — film titles, sayings, team in-jokes (up to 200 characters each). Choose phrases a player could tell with a handful of emoji and the room could guess; avoid abstract or very long ones.
pack_typeYesWhich game the pack is for: "trivia" (Trivia Blitz), "faker" (Imposter) or "emoji_story" (Emoji Story).
questionsNoFor pack_type "trivia" only: the questions, 100 at most. Each has text (up to 300 characters), exactly four options (up to 100 characters each) and correct_index, the 0-based index of the right option. Make the three wrong options plausible, keep options similar in length, and vary which position is correct. Ten to twenty questions makes a good game.
word_groupsNoFor pack_type "faker" only, instead of words, when the pack covers several themes (a company pack with tools, meetings and snacks): up to 50 groups, each with a name and at least 2 words of the same kind. A round deals both of its words from one group, so the imposter's word is always a near miss ("Slack" against "Teams", never "Slack" against "Biscuits"). Four or more words per group plays best; 500 words at most across all groups.

Output Schema

NameRequiredDescriptionDefault
nameYes
game_nameYes
game_typeYes
pack_typeYes
item_countYes
manage_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / questions / items / properties / explanation
      Added value: +{
      +  "description": "Optional. One line on why the answer is right, shown to the room after the question closes (up to 300 characters). Worth adding for company or onboarding facts.",
      +  "type": "string"
      +}
    • addedInput schema / properties / word_groups
      Added value: +{
      +  "description": "For pack_type \"faker\" only, instead of words, when the pack covers several themes (a company pack with tools, meetings and snacks): up to 50 groups, each with a name and at least 2 words of the same kind. A round deals both of its words from one group, so the imposter's word is always a near miss (\"Slack\" against \"Teams\", never \"Slack\" against \"Biscuits\"). Four or more words per group plays best; 500 words at most across all groups.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "name": {
      +        "description": "What the group's words have in common, e.g. \"Our tools\". Up to 40 characters; players never see it.",
      +        "type": "string"
      +      },
      +      "words": {
      +        "description": "At least two words or short phrases of the same kind.",
      +        "items": {
      +          "type": "string"
      +        },
      +        "minItems": 2,
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "name",
      +      "words"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 50,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • changedInput schema / properties / words / description
      Previous value: -"For pack_type \"faker\" only: 2–500 related words or short phrases (up to 100 characters each). Each round pairs two of them — one for the group, a near miss for the imposter — so they should all belong to one theme. Pick words close enough that the imposter can bluff (e.g. \"latte\", \"espresso\", \"cappuccino\"), not opposites or unrelated words. Ten or more gives variety across rounds."New value: +"For pack_type \"faker\" only, when every word belongs to ONE theme: 2–500 related words or short phrases (up to 100 characters each). Each round pairs any two of them — one for the group, a near miss for the imposter — so they must all be the same kind of thing. Pick words close enough that the imposter can bluff (e.g. \"latte\", \"espresso\", \"cappuccino\"), not opposites or unrelated words. Ten or more gives variety across rounds. If the pack covers more than one theme, send word_groups instead."
  2. Changed3 schema fields changed
    • changedInput schema / properties / phrases / description
      Previous value: -"For pack_type \"emoji_story\" only: 1–500 phrases for players to tell in emoji — film titles, sayings, team in-jokes (up to 200 characters each)."New value: +"For pack_type \"emoji_story\" only: 1–500 phrases for players to tell in emoji — film titles, sayings, team in-jokes (up to 200 characters each). Choose phrases a player could tell with a handful of emoji and the room could guess; avoid abstract or very long ones."
    • changedInput schema / properties / questions / description
      Previous value: -"For pack_type \"trivia\" only: the questions, 100 at most. Each has text (up to 300 characters), exactly four options (up to 100 characters each) and correct_index, the 0-based index of the right option."New value: +"For pack_type \"trivia\" only: the questions, 100 at most. Each has text (up to 300 characters), exactly four options (up to 100 characters each) and correct_index, the 0-based index of the right option. Make the three wrong options plausible, keep options similar in length, and vary which position is correct. Ten to twenty questions makes a good game."
    • changedInput schema / properties / words / description
      Previous value: -"For pack_type \"faker\" only: 2–500 related words or short phrases (up to 100 characters each). Each round pairs two of them — one for the group, a near miss for the imposter — so they should all belong to one theme."New value: +"For pack_type \"faker\" only: 2–500 related words or short phrases (up to 100 characters each). Each round pairs two of them — one for the group, a near miss for the imposter — so they should all belong to one theme. Pick words close enough that the imposter can bluff (e.g. \"latte\", \"espresso\", \"cappuccino\"), not opposites or unrelated words. Ten or more gives variety across rounds."
  3. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only cover the safety profile (readOnly=false, destructive=false, openWorld=false). The description adds behavior beyond that: the pack supersedes built-in game content, the host must select it in the lobby before Start, and a Pro/Business plan caps how many packs a team may keep. It does not say what happens when the plan cap is hit or whether packs can later be edited/deleted, which keeps this below 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.

Conciseness4/5

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

Front-loads the action and pack_type mapping, then layers constraints (game scope, content placement, lobby behavior, plan gate) in a logical order. It runs several sentences long, but each carries a distinct constraint; minor redundancy between "so the team plays their own material" and "replaces the game's built-in content" is the only waste.

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?

With an output schema present and annotations carrying safety, the description adequately covers conditional content selection, game eligibility, plan gating and lobby workflow. The remaining gap is failure semantics — what to do if the team lacks Pro/Business or is at its pack cap.

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; the description still adds a cross-parameter rule the schema cannot express — send content in the one list matching pack_type, and for Imposter either words or word_groups, never both. It also points the agent to the per-list schema descriptions for content quality rather than repeating them.

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 ("Create a custom content pack") and immediately enumerates the three target games with their exact pack_type values (trivia, faker, emoji_story). It also distinguishes the effect from built-in content: "A custom pack replaces the game's built-in content with the team's own".

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit negative rule — "Only these three games take custom packs; for any other game, say so rather than calling this" — and a concrete prerequisite action with a named sibling: "call funfriday_get_team first if unsure" about plan/quota. Both the trigger and the exclusion are stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources