Create a new data connection in a Hex workspace by specifying a name, connection type, and type-specific connection details.
Create a new data connection in the workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Connection name | |
| type | Yes | Connection type (snowflake, bigquery, postgres, etc.) | |
| description | No | ||
| connectionDetails | Yes | Connection details (type-specific) |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It states only that a connection is created in the workspace; it says nothing about required permissions, whether the connection is immediately usable, what happens on duplicate names, or what is returned.
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?
A single efficient sentence, front-loaded and free of waste. It is concise, though arguably too terse for a 4-parameter mutation tool.
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 no annotations, no output schema, and a nested type-dependent object, the definition is under-specified. It omits auth requirements, duplicate handling, and the shape of connectionDetails that the agent must supply.
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 coverage is 75%, and the description adds no parameter meaning at all. The type-specific nested 'connectionDetails' object is the most error-prone input and neither the schema nor the description explains its per-type shape, so the description fails to compensate for the gap.
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+resource ('Create a new data connection') and the scope ('in the workspace'), which distinguishes it from siblings like hex-get-data-connection, hex-list-data-connections, and hex-edit-data-connection. It doesn't explicitly name those siblings, but the verb makes the distinction clear enough.
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?
No when-to-use guidance, no prerequisites, and no mention of alternatives such as hex-edit-data-connection or hex-update-data-connection-schema. The agent must infer that creation happens before editing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.