Skip to main content
Glama

Save Cloud Code settings

save_cloud_code
Destructive

PARTIAL SAVE: writes ONLY the 'CloudCode' field of TitlePublicConfigurationModel; all other v1/v2 fields stay untouched. Server-side scripting (CloudCode): the active JavaScript revision the title runs, plus execution policy — engine limits, rate limits, per-handler metadata, whether logs/stack traces are revealed to clients. Scripts are the ONLY way to write protected player data (UserCustomData ReadOnly/Internal buckets) and mutable title data (TitleCustomData Runtime scope). Prefer the dedicated cloud-code tools over editing this section by hand: they compute the code hash, bump the revision number and archive the previous one.

Input Schema

NameRequiredDescriptionDefault
valueYesNew value for the CloudCode field.
title_idYesTitleID, для которого сохраняются данные.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / definitions / ResourceEntryType / enum
      Previous value: -[
      -  "Item",
      -  "VirtualCurrency",
      -  "CryptoCurrency",
      -  "Purchase",
      -  "RewardedVideoCredit",
      -  "PlatformCoin"
      -]New value: +[
      +  "Item",
      +  "VirtualCurrency",
      +  "CryptoCurrency",
      +  "Purchase",
      +  "RewardedVideoCredit",
      +  "PlatformCredits"
      +]
    • changedInput schema / definitions / ResourceEntryType / x-enum-descriptions
      Previous value: -[
      -  "Catalog item. Requires CatalogID, ItemID and Amount.",
      -  "In-game (off-chain) virtual currency. Requires CurrencyID and Amount. Looked up in cfg.Currency.VirtualCurrencies.",
      -  "On-chain cryptocurrency. Requires CurrencyID and Amount. Looked up in cfg.Currency.CryptoCurrencies.",
      -  "Real-money payment in a store. Requires only ProductID (a product from cfg.Purchase.Products); the amount and currency are decided by the store from the SKU price tier. NOT a storable resource and never passes through ResourceService — the money is paid outside before the server learns about it, so the entry is consumed by the receipt check (ExternalPaymentGate) and stripped before the resource operation. Allowed only in Consume and only for Consumable products.",
      -  "Rewarded-video credit. One credit equals one verified ad view that can be spent in systems requiring rewarded video (lootbox open, reward double, re-roll, booster). Granted +1 per server-verified view, or as N from milestones/quests/premium perks; spent -1 per gated action.",
      -  "Payment in Coin, the PLATFORM currency on the player's iDos Games account. Requires only Amount — the price in whole Coin. Like Purchase it is NOT a player resource and never enters ResourceService: it is settled by PlatformCoinPayment in the same transaction as the grant (buyer charged, author credited). Accepted only by the store (Store.Purchase) for now; allowed only in Consume."
      -]New value: +[
      +  "Catalog item. Requires CatalogID, ItemID and Amount.",
      +  "In-game (off-chain) virtual currency. Requires CurrencyID and Amount. Looked up in cfg.Currency.VirtualCurrencies.",
      +  "On-chain cryptocurrency. Requires CurrencyID and Amount. Looked up in cfg.Currency.CryptoCurrencies.",
      +  "Real-money payment in a store. Requires only ProductID (a product from cfg.Purchase.Products); the amount and currency are decided by the store from the SKU price tier. NOT a storable resource and never passes through ResourceService — the money is paid outside before the server learns about it, so the entry is consumed by the receipt check (ExternalPaymentGate) and stripped before the resource operation. Allowed only in Consume and only for Consumable products.",
      +  "Rewarded-video credit. One credit equals one verified ad view that can be spent in systems requiring rewarded video (lootbox open, reward double, re-roll, booster). Granted +1 per server-verified view, or as N from milestones/quests/premium perks; spent -1 per gated action.",
      +  "Payment in Credits, the PLATFORM currency on the player's iDos Games account (players see it as \"Aspis\" — write Aspis in player-facing text). Requires only Amount — the price in whole Credits. Like Purchase it is NOT a player resource and never enters ResourceService: it is settled by PlatformCreditsPayment in the same transaction as the grant (buyer charged, author credited). Accepted only by the store (Store.Purchase) for now; allowed only in Consume."
      +]
    • changedInput schema / definitions / ResourceEntryType / x-enumNames
      Previous value: -[
      -  "Item",
      -  "VirtualCurrency",
      -  "CryptoCurrency",
      -  "Purchase",
      -  "RewardedVideoCredit",
      -  "PlatformCoin"
      -]New value: +[
      +  "Item",
      +  "VirtualCurrency",
      +  "CryptoCurrency",
      +  "Purchase",
      +  "RewardedVideoCredit",
      +  "PlatformCredits"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / definitions / ResourceEntryType / enum
      Previous value: -[
      -  "Item",
      -  "VirtualCurrency",
      -  "CryptoCurrency",
      -  "Purchase",
      -  "RewardedVideoCredit"
      -]New value: +[
      +  "Item",
      +  "VirtualCurrency",
      +  "CryptoCurrency",
      +  "Purchase",
      +  "RewardedVideoCredit",
      +  "PlatformCoin"
      +]
    • changedInput schema / definitions / ResourceEntryType / x-enum-descriptions
      Previous value: -[
      -  "Catalog item. Requires CatalogID, ItemID and Amount.",
      -  "In-game (off-chain) virtual currency. Requires CurrencyID and Amount. Looked up in cfg.Currency.VirtualCurrencies.",
      -  "On-chain cryptocurrency. Requires CurrencyID and Amount. Looked up in cfg.Currency.CryptoCurrencies.",
      -  "Real-money payment in a store. Requires only ProductID (a product from cfg.Purchase.Products); the amount and currency are decided by the store from the SKU price tier. NOT a storable resource and never passes through ResourceService — the money is paid outside before the server learns about it, so the entry is consumed by the receipt check (ExternalPaymentGate) and stripped before the resource operation. Allowed only in Consume and only for Consumable products.",
      -  "Rewarded-video credit. One credit equals one verified ad view that can be spent in systems requiring rewarded video (lootbox open, reward double, re-roll, booster). Granted +1 per server-verified view, or as N from milestones/quests/premium perks; spent -1 per gated action."
      -]New value: +[
      +  "Catalog item. Requires CatalogID, ItemID and Amount.",
      +  "In-game (off-chain) virtual currency. Requires CurrencyID and Amount. Looked up in cfg.Currency.VirtualCurrencies.",
      +  "On-chain cryptocurrency. Requires CurrencyID and Amount. Looked up in cfg.Currency.CryptoCurrencies.",
      +  "Real-money payment in a store. Requires only ProductID (a product from cfg.Purchase.Products); the amount and currency are decided by the store from the SKU price tier. NOT a storable resource and never passes through ResourceService — the money is paid outside before the server learns about it, so the entry is consumed by the receipt check (ExternalPaymentGate) and stripped before the resource operation. Allowed only in Consume and only for Consumable products.",
      +  "Rewarded-video credit. One credit equals one verified ad view that can be spent in systems requiring rewarded video (lootbox open, reward double, re-roll, booster). Granted +1 per server-verified view, or as N from milestones/quests/premium perks; spent -1 per gated action.",
      +  "Payment in Coin, the PLATFORM currency on the player's iDos Games account. Requires only Amount — the price in whole Coin. Like Purchase it is NOT a player resource and never enters ResourceService: it is settled by PlatformCoinPayment in the same transaction as the grant (buyer charged, author credited). Accepted only by the store (Store.Purchase) for now; allowed only in Consume."
      +]
    • changedInput schema / definitions / ResourceEntryType / x-enumNames
      Previous value: -[
      -  "Item",
      -  "VirtualCurrency",
      -  "CryptoCurrency",
      -  "Purchase",
      -  "RewardedVideoCredit"
      -]New value: +[
      +  "Item",
      +  "VirtualCurrency",
      +  "CryptoCurrency",
      +  "Purchase",
      +  "RewardedVideoCredit",
      +  "PlatformCoin"
      +]
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, so the description's job is to explain what is actually overwritten, and it does: only the CloudCode field changes, other v1/v2 fields are preserved. It also warns that doing this by hand skips code-hash computation, revision bumping and archiving. The remaining gap is whether the supplied `value` object fully replaces the existing CloudCode section (dropping omitted sub-fields) or merges — an important detail for a destructive write that goes unstated.

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 partial-save constraint in capitals, which is the single most decision-relevant fact, then describes the payload and the alternative. Dense but nearly every clause carries information; the protected-data aside (UserCustomData buckets, Runtime title data) is background that is only loosely relevant to calling this tool.

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 two-parameter tool with a deeply nested payload and full schema descriptions, the description supplies the conceptual model an agent needs before constructing the value object, and annotations cover the safety profile. No output schema exists, and the description says nothing about what a successful save returns or how failures surface, which is the main omission.

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 earns above that by characterizing what the two parameters carry — the CloudCode section as the active JavaScript revision plus execution policy (engine limits, rate limits, handler metadata, log/stack-trace exposure) and the title scope. It adds conceptual grouping that the flat property list does not convey.

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?

Opens with a specific verb and scope: writes ONLY the 'CloudCode' field of TitlePublicConfigurationModel. This immediately distinguishes it from the many other save_* siblings that write whole configuration sections, and the description of what the CloudCode section contains (active JS revision plus execution policy) makes the resource concrete.

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 steers the agent away from hand-editing this section: 'Prefer the dedicated cloud-code tools over editing this section by hand: they compute the code hash, bump the revision number and archive the previous one.' That names the reason for the alternative but not the sibling by name (publish_cloud_code), and gives no positive statement of when this tool IS the right choice (e.g. changing rate limits or resource policy without touching code).

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.