Skip to main content
Glama

Send Original Item as Gift

horizon_send_item_gift
DestructiveIdempotent

Sends one original unequipped item privately to another player, charging the confirmed sender fee and creating a seven-day Inbox gift offer.

Instructions

Sends one original unequipped item privately to another player under the confirmed fee configuration. Use when: explicit private item gift actions after reading horizon://docs/item-gifts. Claim offers and returns with horizon_claim_inbox. Not for: automatic gifting, polling or generated replacement operations. Use horizon_get_item_gift_operation to reconcile the original intent. Requires: userId and the player's session: sign in with horizon_signin_email or horizon_signin_anonymous and pass its accessToken as sessionToken. Side effects: One HTTP attempt. Persist all seven original fields before sending under project/player/feature. Atomically moves the exact inventory instance into escrow, charges the fixed sender fee (never refunded) and delivers an Inbox offer that expires after seven days. Resolve a friend code with horizon_find_player first. Never recalculate revisions after a lost response. Returns: {receipt,gift,replayed,serverTime}; 201 new, 200 identical replay Errors: 409 REVISION_CONFLICT, OPERATION_CONFLICT, OPERATION_EXPIRED, STATE_CONFLICT and GIFT_EXPIRED, GIFT_DECLINED, GIFT_ALREADY_CLAIMED, GIFT_UNAVAILABLE need explicit reconciliation, never fresh revisions or operation IDs on an unknown outcome. Missing OPERATION_NOT_FOUND does not prove nonexecution. RECIPIENT_INBOX_FULL and 422 SELF_GIFT, ITEM_EQUIPPED, OPEN_GIFT_LIMIT_REACHED, GIFT_LIMIT_REACHED, INSUFFICIENT_BALANCE withdraw and charge nothing. 403 ITEM_GIFTS_DISABLED. 404 RECIPIENT_NOT_FOUND hides blocks. 429 ITEM_GIFTS_RATE_LIMITED schedules no retry. 401 means the session is missing or expired: sign in again and retry with the new accessToken. 403 for a session means the token belongs to another user: pass the userId that signed in. 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": {
      "userId": "<userId>",
      "sessionToken": "<sessionToken>",
      "operationId": "<operationId>",
      "issuedAt": "<issuedAt>",
      "recipientId": "<recipientId>",
      "instanceId": "<instanceId>",
      "expectedInventoryRevision": "<expectedInventoryRevision>",
      "expectedConfigRevision": "<expectedConfigRevision>"
    },
    "name": "horizon_send_item_gift"
  }
}

Input Schema

NameRequiredDescriptionDefault
userIdYesActive player matching the current session and project
issuedAtYesOriginal canonical timestamp including .SSSZ; never replace issuedAt on retry
instanceIdYesExact original unequipped item instance ID
operationIdYesPersisted original operation UUID, never replaced after uncertainty
recipientIdYesRecipient player ID, resolved from a friend code with horizon_find_player
sessionTokenYesCurrent accessToken sent only as Bearer
expectedConfigRevisionYesOriginal gift config revision whose fee and currency the player confirmed
expectedInventoryRevisionYesExact original safe-integer revision; never refresh-and-retry a mutation

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.11.1

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing that the fee is never refunded, that the exact inventory instance moves atomically into escrow, that the offer expires after seven days, and that there is one HTTP attempt only. It also spells out failure semantics: 409/expired conflicts require reconciliation, OPERATION_NOT_FOUND does not prove non-execution, and 429 schedules no retry. This matches destructiveHint and idempotentHint rather than contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Section labels (Use when, Not for, Requires, Side effects, Returns, Errors) make it front-loaded and scannable despite its length. However, the error catalog repeats itself: 401 handling and the 429 rate-limit meaning are each stated twice, and 403 semantics are split across entries, which is wasted space in an already dense block.

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 destructive, idempotent mutation with no output schema, the description covers authentication prerequisites, side effects, return payload shape, HTTP status meanings, and replay behavior (201 new vs. 200 identical replay). An agent has everything needed to call it and interpret the outcome without additional context.

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 cross-field intent: persist all seven original fields before sending, never generate fresh revisions or operation IDs on an unknown outcome, and resolve the recipient from a friend code first. That is real meaning beyond per-field descriptions, though it does not explain every field.

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, resource, and scope: sends exactly one original unequipped item privately, under a confirmed fee configuration. It is clearly distinguishable from generated-replacement paths and from claim flows, which it names as separate tools.

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?

Explicit 'Use when' and 'Not for' clauses with named alternatives: claim via horizon_claim_inbox, reconcile via horizon_get_item_gift_operation, resolve friend codes via horizon_find_player, authenticate via horizon_signin_email or horizon_signin_anonymous. Nothing is left to inference.

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