What's the difference between tool calling and function calling?

There’s no real difference between tool calling and function calling: they’re names for the same mechanism, used by different vendors. OpenAI and Google’s APIs call it function calling, Anthropic calls it tool use, and tool calling is the vendor-neutral term that covers both. In every case the model is given a schema, a name, a description, and arguments, and emits a structured call against it instead of writing free text.

Where a real distinction sometimes gets drawn: function can imply something narrower, a single deterministic operation with typed inputs and outputs, like a calculator or a database lookup. Tool gets used more loosely to also cover things that are not pure functions: a web search, a code interpreter, a sub-agent, or a whole MCP server exposing several operations behind one connection. That distinction is informal, not a spec boundary, and the two terms get used interchangeably in most writing on the subject, this page included.

See also: What’s the difference between MCP and a plain API call?

keep reading

More on this.

Two ways to run Tessary.

Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.

Tessary Cloud

We host it for you. Send your first trace with nothing to deploy and no model key.

what's includedper organization
traces
10,000 per calendar month
stored trace data
1 GB
retention
30 days
model credit
$10, one-time, for triage and root-cause analysis
credit card
not required

Self-hosted Tessary

Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.

Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md

docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y