# Apple 'Agent Seer' research: API and parameter design break agent tool-calling

> Updated 2026-09-01 · type: news · category: ai-infrastructure · status: active · rev 1

Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and…

- Open source: unknown

- **Canonical:** https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/
- **Source:** [X · @IntuitMachine (research summary)](https://x.com/IntuitMachine/status/2094727051987108244)
- **Tags:** ai-infrastructure, news, agents, governance

---

Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and documentation — rather than model capability. Practical implication for GTM-agent builders: design tool surfaces for the model, and keep a human approval step on consequential actions.

## Notes

- Summarised from an X research thread (2026-09-01); the primary paper was not independently verified for this entry — treat specific failure percentages as unconfirmed.
- Curated from the GTM Stacker signal registry (registry_update pass, briefs 2026-09-01→08).