Tools And Mid Call Function Calling

Operator declares a tool with name='check_balance' but no parameters JSON schema. Model emits tool calls with random argument shapes.

Define every tool with the documented OpenAI-style schema {name, description, parameters: {type:'object', properties, required}}. The model uses the JSON Schema to format arguments; without it the arg JSON is ad-hoc and breaks serverUrl handlers.

Tool 'send_followup_sms' is long-running and the operator does not want to block the assistant. They mark it async:true.

async:true makes Vapi not wait for a result before continuing the conversation. Operator's serverUrl still returns 2xx promptly and runs the work in background. Do not use async:true for tools whose result must be spoken — the assistant won't see the response.

Customer asks 'what's my balance?' Tool round-trips in 1.5s and customer hears dead air while the assistant waits.

Set blocking:false (the default) and configure messages with type 'request-start' so the assistant speaks a filler phrase ('one sec, checking that') during tool execution. Use 'request-complete' and 'request-failed' messages to bracket the result.