warehouses_resize_warehouseChange a Snowflake warehouse's compute size (e.g., XSMALL to LARGE) to match workload demands and control resource usage.
Change warehouse compute size (XSMALL, SMALL, MEDIUM, LARGE, XLARGE, 2XLARGE, etc.).
| Name | Required | Description | Default |
|---|---|---|---|
| size | Yes | ||
| warehouse_name | Yes | Quote names that aren't all uppercase, exactly as list tools return them. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v3.0.0Input schema / properties / warehouse_name / descriptionAdded value: +"Quote names that aren't all uppercase, exactly as list tools return them."v2.0.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-destructive, non-idempotent, open-world mutation, so the safety profile is covered. The description adds the size vocabulary but omits operationally important behavior: whether the resize applies immediately or after in-flight queries finish, and the cost implication of sizing up. Some added value, clear gaps.
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 front-loaded sentence with no preamble — appropriately sized. The trailing 'etc.' is the one weak element, weakly hedging where a definitive list or a pointer to a canonical source would be better.
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?
An output schema exists so return values needn't be described, and there are only two required parameters. What's missing is contextual: the effect on currently running queries and the cost/latency consequence of a resize, which matter for an agent deciding whether to invoke this at all.
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 only 50%: warehouse_name is documented inline (quote non-uppercase names), while size has no schema description. The description partially compensates by listing valid size values, but the trailing 'etc.' leaves the accepted set ambiguous and nothing explains whether a string like 'MEDIUM' versus 'medium' is accepted.
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 ('Change warehouse compute size') and enumerates valid sizes, which distinguishes it from resume/suspend/create/drop siblings sharing the warehouse prefix. It stops short of naming those siblings explicitly, but the action is unambiguous.
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 resize versus suspending, resuming, or recreating a warehouse, and no prerequisites are mentioned. An agent must already know the Snowflake warehouse model to pick this tool confidently.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.