Curiosity · Syllabus

Tool Calling and Function Calling in a B.Tech — syllabus & what you learn

'Function calling' here means an LLM requesting an external tool in a structured format. It is not the ordinary programming-language act of calling a function, which is covered in the core programming courses. Tool calling lets a language model emit a structured request that the surrounding program executes — a search, a database query, an API call — and then feed the result back into the model. It is what turns a text generator into a system that can act. Inside a four-year B.Tech, Tool Calling and Function Calling arrives in layers: programming and mathematics foundations in years one and two, core methods next, and applied depth concentrated in years three and four plus the capstone. Using Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura's B.Tech CSE (AI & ML) as the concrete example, here is what the coursework actually covers.

At a glance

Topic
Tool Calling and Function Calling
VSET programme
B.Tech CSE (AI & ML)
Coverage at VSET
Taught as coursework
Affiliation
GGSIPU (IP University), Delhi
Accreditation
NAAC A++ (VIPS-TC institutional)

How VSET teaches Tool Calling and Function Calling

Tool calling lets a language model emit a structured request that the surrounding program executes — a search, a database query, an API call — and then feed the result back into the model. It is what turns a text generator into a system that can act. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • VSET publishes a 160+ page Model Context Protocol library at learn.engineering.vips.edu, which is centrally about how models call tools.
  • The ~100 page agent-protocols library covers the surrounding agent-to-agent layer.
  • Framework-level tool use is documented through LangChain, LangGraph, CrewAI and AutoGen in the same curriculum.
  • Delivered inside the B.Tech CSE (AI & ML) track, one of VSET's seven GGSIPU-affiliated B.Tech programmes.

Labs and infrastructure

  • Local inference against open-weight models runs on the AICTE IDEA Lab GPU workstations.
  • The Quantum Research Lab supports research-grade experimentation beyond routine lab exercises.

What students actually build

  • Building MCP servers — which define exactly what tools a model may call — is an explicit part of the VSET capstone pattern.
  • Student-built MCP servers expose tools and data to LangGraph multi-agent orchestrators.

Frequently asked questions

When does Tool Calling and Function Calling content actually start in a B.Tech?

Meaningful Tool Calling and Function Calling content typically ramps up from the second or third year, after programming and mathematics foundations. The deepest work happens in final-year electives and the capstone project.

How deeply is tool calling covered at VSET?

Very: the published MCP library runs to more than 160 pages and is precisely about the model-to-tool interface, alongside a ~100 page agent-protocols library.

Do students implement tool calling themselves?

Yes — building MCP servers is a named capstone project type, and those servers define the tools an agent is allowed to invoke.

Which frameworks are used?

LangChain, LangGraph, CrewAI and AutoGen are all documented in the published curriculum.

Sources

  1. VSET — Artificial Intelligence department — accessed 2026-08-31
  2. VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
  3. GGSIPU — IP University — accessed 2026-08-31

Related