Run LLM completion using Snowflake Cortex AI by sending a prompt, with optional model, max tokens, and temperature settings.
Run LLM completion using Snowflake Cortex AI (e.g., 'llama3.3-70b', 'mistral-large2', 'snowflake-arctic').
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | llama3.3-70b | |
| prompt | Yes | ||
| max_tokens | No | ||
| temperature | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.1.5Input schema / properties / model / defaultPrevious value: -"claude-3-5-sonnet"New value: +"llama3.3-70b"v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action ('Run LLM completion') and example models, saying nothing about side effects, whether the operation is read-only, output format, cost implications, or error behavior. For a tool with zero annotation coverage, this is a significant gap.
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?
The description is a single, focused sentence with no filler or redundant content. It front-loads the core action and immediately provides useful examples. Every word earns its place.
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?
The tool is relatively simple with 4 parameters, 1 required, and an output schema exists, so return values need no description. However, the description omits usage context versus sibling Cortex tools and fails to provide behavioral details like non-mutating guarantees. It is adequate for basic invocation but leaves gaps in decision-making.
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 0%, so the description must compensate. It adds model examples ('llama3.3-70b', 'mistral-large2', 'snowflake-arctic'), which gives some parameter semantics for the model field. However, it does not explain prompt, max_tokens, or temperature, leaving these undocumented in both the schema and the description.
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: 'Run LLM completion using Snowflake Cortex AI' with concrete model examples. This clearly differentiates it from sibling tools like snowflake_cortex_summarize, snowflake_cortex_translate, and other specialized Cortex functions, which perform narrower tasks. An agent can immediately understand this is the general-purpose LLM generation tool.
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?
The description implies usage as a general completion tool through the phrase 'Run LLM completion', but it does not explicitly state when to prefer this over siblings like cortex_summarize or cortex_sentiment. There are no explicit alternatives or exclusion conditions, leaving the choice to inference from the tool name and sibling purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.