Skip to main content
Glama

Sign Up Anonymously

horizon_signup_anonymous

Creates an anonymous guest player account from a display name and returns an anonymousToken for first-launch guest play without email. Use only for new guests, not email signups or returning guests.

Instructions

Creates a new anonymous (guest) player account that needs only a display name and returns its anonymousToken. Use when: a player starts without email, for example on first launch of a game with guest play. Not for: players who sign up with email and password (use horizon_signup_email) or returning guests (use horizon_signin_anonymous with the stored anonymousToken). Side effects: creates one new player account per call after the player chooses guest play. Omitted/false includeRefreshToken starts no session; true also issues access and refresh tokens. Never automatically repeat an uncertain signup. Returns: {userId, username, isAnonymous: true, anonymousToken, authStatus, createdAt}, plus session tokens only when opted in. The server alone issues the 32-character anonymousToken. Store it in platform secure storage. Without accessToken, call horizon_signin_anonymous. Errors: 400 for an invalid displayName: fix the name and retry. Needs HORIZON_API_KEY. Every failure returns an error result (isError) with the HTTP status and body: a 401 that horizon_test_connection also returns means HORIZON_API_KEY is wrong, 429 means the account's per-minute rate limit was reached (wait a minute, then retry).

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": {
      "displayName": "<displayName>"
    },
    "name": "horizon_signup_anonymous"
  }
}

Input Schema

NameRequiredDescriptionDefault
displayNameYesDisplay name shown on leaderboards (max 30 characters)
includeRefreshTokenNoExplicit opt-in to a rotating 30-day refresh session; omitted or false preserves access-only behavior. Store refresh tokens in platform secure storage

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.11.1
    • addedInput schema / properties / includeRefreshToken
      Added value: +{
      +  "description": "Explicit opt-in to a rotating 30-day refresh session; omitted or false preserves access-only behavior. Store refresh tokens in platform secure storage",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changedv1.6.0
    • changedInput schema / properties / displayName / description
      Previous value: -"Display name for the anonymous user (max 30 characters)"New value: +"Display name shown on leaderboards (max 30 characters)"
  3. First observedv1.5.4

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare openWorldHint=true, idempotentHint=false and destructiveHint=false, and the description goes well beyond them: it discloses that exactly one account is created per call, that includeRefreshToken controls whether a session is issued at all, that the server alone mints the 32-character token and it must go to secure storage, and that HORIZON_API_KEY is required. Error mapping (400 bad name, 401 bad key cross-checked against horizon_test_connection, 429 per-minute limit) is unusually complete for a mutation. It stops short of nothing material, though token lifetime/rotation detail is only partially covered.

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?

Well front-loaded with labeled sections (Use when / Not for / Side effects / Returns / Errors) so the agent can scan the routing decision first. It is long, and the secure-storage instruction is repeated in both the description and the includeRefreshToken schema text, but no sentence is pure filler.

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?

For a non-idempotent account-creation mutation with no output schema, the definition supplies the return shape inline, session-token opt-in behavior, storage obligations, the required API key, and per-status error handling. An agent has everything needed to call it once and handle both success and failure paths.

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 defines both parameters, giving a baseline of 3. The description adds real behavioral meaning beyond that: omitted/false includeRefreshToken means no session is started, true issues access and refresh tokens, and an invalid displayName produces a 400 to be fixed and retried — semantics the schema's field-level text does not state.

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 ('Creates a new anonymous (guest) player account') and immediately bounds the scope ('needs only a display name and returns its anonymousToken'). It explicitly distinguishes itself from horizon_signup_email and horizon_signin_anonymous, so an agent can route correctly without inspecting sibling schemas.

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?

Contains explicit 'Use when' (player starts without email, first launch guest play) and 'Not for' clauses that name the two competing tools and the condition selecting each (email signup vs. returning guest with stored anonymousToken). The retry guidance ('Never automatically repeat an uncertain signup') is a concrete when-not rule for a non-idempotent call.

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

Deploy Server

Other Tools