horizon_save_cloud_dataSave a user's cloud data string (up to 300,000 characters) on horizOn by providing a UUID and data payload for persistent game or app storage.
Saves cloud data for a user on horizOn. Data is a string (max 300,000 characters).
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Save data string (max 300,000 characters) | |
| userId | Yes | User ID (UUID) |
Changes observed during successful MCP inspections.
v1.5.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden, and it delivers little. It omits the critical write semantics: whether saving overwrites or merges existing cloud data, whether the user must be signed in, and whether the call is idempotent. Only the size limit is disclosed, and that is already in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, front-loaded sentences with no padding. It loses a point only because the second sentence duplicates the maxLength constraint already present in the schema instead of spending that space on behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with zero annotations, no output schema, and opaque payload semantics, the description is not complete enough. It never says what the call returns (or whether it can fail), nor how the saved data relates to the data returned by horizon_load_cloud_data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% — both userId and data are documented with format and maxLength — so baseline 3 applies. The description's restatement of the 300,000-character limit adds nothing beyond the schema, and it says nothing about the meaning or expected shape of the opaque 'data' string.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Saves cloud data for a user') on a named platform, which is enough for basic selection. However, it never distinguishes itself from its obvious sibling horizon_load_cloud_data, and the odd 'horizOn' capitalization is noise rather than signal.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this instead of load_cloud_data or any other persistence tool, no prerequisite (e.g. authentication required), and no mention of what happens to previously saved data. The agent must infer all usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.