Skip to main content
Glama
Sign In

iDos Games

by com.idosgames
OverviewDiscussionsAdmin

Save Game Spec settings

save_game_spec
Destructive

PARTIAL SAVE: writes ONLY the 'GameSpec' field of TitlePublicConfigurationModel; all other v1/v2 fields stay untouched. GameSpec - the WHOLE game of a game-constructor title (module kit-game) as data, stored as ONE JSON string (a JSON object serialized to text). The game reads it at sign-in and plays it; a spec that does not validate runs the built-in demo and logs why. Shape (format v1): {"v":1, "engine":"phaser", "seed"?:string, "modes":[{"id", "preset" (a genre preset id, e.g. "runner"), "role":"core"|"meta"|"embedded", "params"?:{preset params, e.g. difficulty 0..1, generosity 0..1, lanes, lives}, "blockParams"?:{blockId:{param:value}} }], "resources"?:[{"id" (snake_case), "kind":"currency"|"item"|"score"|"local", "ref"? (the title's currency/item id for currency/item), "name"? (text key)}], "flows"?:[{who produces/consumes which resource}], "rules"?:[{"id", "on" (event), "when"? (formula), "do":[effects]}], "palette"?:{role:"#rrggbb"} (roles background, ground, lane, primary, secondary, danger, coin, accent, text, muted), "texts"?:{key:{language:text}} (keys title, hint and the resource name keys), "rewards"?:{"adMultiplier":3, "vipMultiplier":5}}. A currency/item resource needs a source and a sink (a mode or system: like system:store). Unknown fields are kept. Max 64 KB; v must be an integer >= 1. Edit by reading it with get_game_spec, changing the JSON and saving the whole string back.

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": {
      "title_id": "<title_id>",
      "value": "<value>"
    },
    "name": "save_game_spec"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial context beyond the destructiveHint annotation: the write replaces one field only, the value is a whole JSON string that must be replaced intact, an invalid spec falls back to the built-in demo with logged reasons, unknown fields are preserved, and a 64 KB cap applies. These are exactly the consequences an agent needs before a destructive write.

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 critical PARTIAL SAVE constraint and remains information-dense throughout, but the long inline spec-shape enumeration overlaps with what get_game_spec would return and inflates the length. It is structured rather than rambling, just longer than strictly needed for invocation.

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 no-output-schema write of a structured blob, the description covers scope, format, validation fallout, size limit, and the read-modify-write workflow. Nothing essential for calling it correctly appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, but the description goes well past the schema's 'New value for the GameSpec field' by specifying the JSON format v1 shape, required constraints (v integer >= 1, resource source/sink pairing, snake_case ids, palette roles) and the size limit. This meaningfully improves the chance of a valid call.

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 ('writes ONLY the GameSpec field of TitlePublicConfigurationModel') and explicitly contrasts with the broad save_* family by noting that all other v1/v2 fields stay untouched. An agent can distinguish this from save_title_data without opening either 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?

Gives an explicit edit workflow ('read it with get_game_spec, changing the JSON and saving the whole string back'), which tells the agent when and how to use it. It does not explicitly name when-not-to-use alternatives such as save_title_data for other fields, leaving that partly implicit in the partial-save sentence.

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

All iDos Games toolsInspect
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.

Resources