What does an ideal function-calling schema look like?

medium

Answer

$(\mathrm{verb}_{\mathrm{object}})$
$(2) Human-readable description explaining when to use it.$
$(3) JSON Schema for parameters with required fields, type, description per field, enum for constrained values, format for dates/emails.$
$(4) Examples in the description if the signature is subtle.$
$(5) Return schema: describe what the tool returns so the LLM can interpret results.$
$(6) Keep the tool set small (~5-15) — larger sets need retrieval-based tool selection.$

Check yourself — multiple choice

Random function names
$\mathrm{Verb}_{\mathrm{object}}$ name + rich description + JSON Schema args (types, descriptions, enums, formats) + return schema + few examples
Only names matter
Same across all tools

Function schema: name + description + full JSON schema args + return type + examples.

#function-calling#agents#tools

214 interview questions in this topic.