Keep tool results inside a token budget
Bound every model-visible tool result before it enters the next prompt.
Tool-Calling
AI Systems Need Runtime Budgets
How to bound time, tokens, retries, tool calls, and estimated cost across a complete AI execution instead of limiting each call in isolation.
Cap tool-call loops explicitly
Set a hard iteration limit on automatic function invocation and treat hitting it as an explicit application outcome.
Validate tool arguments at the execution boundary
Treat model-generated tool arguments as untrusted input even when they satisfy the generated schema and bind successfully to the expected C# types.
Describe tool parameters like API contracts
Give AI tools precise parameter names, units, formats, and side-effect expectations so the model receives an unambiguous contract.