cloud_db_createProvision MongoDB, PostgreSQL, or MySQL databases after wallet check; returns a job_id to poll. Use sandbox mode for zero-cost trials without a wallet.
Kiểm tra ví chung rồi tạo MongoDB/PostgreSQL/MySQL; trả job_id để poll. sandbox=true: thử 0đ, không cần ví.
| Name | Required | Description | Default |
|---|---|---|---|
| cpu | No | ||
| engine | No | mongodb | |
| ram_gb | No | ||
| disk_gb | No | ||
| sandbox | No | sandbox=true: thử 0đ, không cần ví | |
| app_name | Yes | ||
| package_slug | No |
Changes observed during successful MCP inspections.
v0.11.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover the safety profile (not read-only, not idempotent, open-world, non-destructive). The description adds real behavioral context beyond that: a wallet-balance precondition, an asynchronous job_id/poll workflow, and the zero-cost sandbox mode. It stops short of stating what happens on insufficient balance or how long the job takes.
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 tight clauses, front-loaded with the core action and immediately followed by the return contract and the cost-saving alternative. No filler, and the empty state (sandbox) is called out at the end where it is easy to scan.
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?
With no output schema, the description correctly supplies the key return contract (job_id to poll) and the wallet requirement, which is essential for a mutation tool. But for a 7-parameter creation tool at 14% schema coverage, the sizing parameters and app_name/package_slug semantics remain undocumented anywhere.
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 only 14% across 7 parameters, so the description has to compensate. It clarifies the engine enum values and the sandbox flag (whose meaning is already duplicated in the schema), but leaves app_name, cpu, ram_gb, disk_gb and package_slug entirely unexplained.
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?
The description states a specific verb and resource ('tạo MongoDB/PostgreSQL/MySQL') plus the billing precondition (wallet check) and the async return contract (job_id để poll). It distinguishes itself from cloud_vps_create and vibecloud_create_database by naming the database engines, though it does not explicitly contrast with those siblings.
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?
It gives one useful usage branch — sandbox=true means a free trial with no wallet required — which implies the non-sandbox path needs a funded shared wallet. However, there is no explicit 'use this instead of X when...' routing to siblings like vibecloud_create_database or cloud_vps_create.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.