Tool compatibility and results matrix

The following reference table outlines how to interpret model validation results and supported Model Provider details using Agent Studio's unified abstraction layer (powered by LiteLLM).

Table 1. Interpretation of Validation Results
Validation status	Interpretation and required actions
Model supports function calling	The model successfully returned a structured tool call. It is fully certified for use in agents and workflows. The UI displays the specific tool invoked, verified arguments, and real-time processing response latency.
Model does not support function calling	The model failed to return a structured tool call and cannot be used to power agents in Agent Studio. Select an alternative model variant or deployment configuration that natively supports tool calling.
Test Error	The request failed due to infrastructure or transport layers, for example, invalid endpoint URL, incorrect credentials, or model provider unavailability. Resolve the underlying connection parameters and retry.

Supported model providers and endpoint requirements

Agent Studio communicates with major cloud providers and custom infrastructures using a consistent model abstraction layer:

Enterprise cloud providers: OpenAI, Azure OpenAI, Google Gemini, Anthropic, and AWS Bedrock. For these standard providers, Agent Studio proactively enforces compatibility and rejects models known to lack function-calling features during registration.
Custom and private deployments: Cloudera AI Inference (CAI) and OpenAI Compatible custom endpoints.

Authoritative validation rule

For Cloudera AI Inference and custom OpenAI-compatible endpoints, function calling capabilities, also called tool calling capabilities cannot always be discovered programmatically ahead of time. The Function Calling Test is the authoritative method to confirm compatibility. If a custom endpoint fails validation, ensure that:

The model serving runtime explicitly has tool calling or function calling modules enabled.
The endpoint exposes a fully OpenAI-compliant chat completions API structure.