This seems a result of relying on the LLM to accurately extract information that needs to be exact.

I touch on this from my own experience: https://youtu.be/cs5cbxDClbM?si=IQIFAD38cVzLCs55&t=486

Basically if you have the actual "factual" information, use it directly instead of hoping the LLM will accurately extract it and use it as part of a function call. In this case they already know what the accurate URLs are, just use it.