How to parse tool calls from OpenAI, Anthropic and Google
How to turn tool calls from different LLM providers into one common interface without losing the identifiers that correlate each result.
Last updated: 14 September 2026.
maximofn.com is the personal blog of Máximo Fernández Núñez. This page explains what data the site processes and what it does not, plainly. It is short because there is little to tell: the site does not collect personal data directly.
Máximo Fernández Núñez, Spain. Contact: maximofn@gmail.com (also on the contact page).
Every page loads the Ahrefs Web Analytics script to know which articles are read. According to Ahrefs it works without cookies and without persistent identifiers: it records page views, referring page, approximate country from the IP and device type, in aggregate. I have verified that it leaves no cookie in the browser. Legal basis: legitimate interest in understanding how the site is used (Art. 6(1)(f) GDPR).
Like any server, these providers see the IP address and browser of each request in their technical logs, which they use to serve the site and for security. None of them sets cookies on this domain.
images.maximofn.com. It may also receive network error reports from the browser (Network Error Logging)./mcp, intended for AI agents.Legal basis: legitimate interest in providing and protecting the service (Art. 6(1)(f) GDPR).
Some articles embed content from other sites. When it loads, your browser connects directly to that third party, which can see your IP and use its own cookies under its own policy:
youtube-nocookie.com domain. Google's policy.Links to other sites (GitHub, LinkedIn, X, YouTube, Hugging Face, Kaggle…) transmit nothing until you click them; from then on each site's own policy applies.
Fonts are served from this same domain, not from Google Fonts or any other external service.
You can exercise your rights of access, rectification, erasure, restriction, portability and objection by writing to maximofn@gmail.com. Since the site collects no personal data directly, in practice the only thing that can exist are the technical logs of the providers listed above. If you believe the processing is not correct, you can lodge a complaint with the Spanish data protection authority, the AEPD.
If the site adds anything that changes the above (a form, another analytics tool, a new third party), this page will be updated and the date at the top will change.
How to turn tool calls from different LLM providers into one common interface without losing the identifiers that correlate each result.
A practical guide to designing tools an LLM can discover, adapting them to any LLM provider, executing them safely, and ...
How the Gymnasia AI agent is built: a BYOK conversational coach with local tools and a food estimator that reads macros ...
Let's talk.
maximofn@gmail.com
Machine Learning and AI specialist. I develop solutions with generative AI, intelligent agents and custom models.
AI agents, powered by LLMs, promise to transform applications. But are they simple executors today or future intelligent collaborators? To reach their...
Learn to create an IA system to execute efficiently on a device
Hugging Face spaces allow us to run models with very simple demos, but what if the demo breaks? Or if the user deletes it? That's why I've created docker containers with some interesting spaces, to be able to use them locally, whatever happens. In fact, if you click on any project view button, it may take you to a space that doesn't work.
Let's talk.
maximofn@gmail.com
Machine Learning and AI specialist. I develop solutions with generative AI, intelligent agents and custom models.
Dataset with jokes in English
Use: Fine-tuning text generation models for humor
Dataset with translations from English to Spanish
Use: Training English-Spanish translation models
Dataset with Netflix movies and series
Use: Netflix catalog analysis and recommendation systems