AI ToolsJul 4, 2026, 10:53 PM

New AI models break tool calls with invented parameters

TickrWire Editorial Desk·Jul 4, 2026, 10:53 PM·1 min read AI-assisted, human-reviewed

Reported by Simon Willison: Better Models: Worse Tools. Analysis and context written by TickrWire.

30-second summary

Claude Opus 4.8 sometimes invents extra fields in tool calls, causing schema mismatches and rejected executions.

TickrWire
Key takeaways
  • Claude Opus 4.8 sometimes invents non-existent fields in tool call arguments, causing schema validation failures.
  • The core edit operation remains functionally correct, but invalid parameters force repeated retries.
  • This issue affects automated workflows relying on strict schema validation for tool calls.
  • The problem underscores a tension between model capability and reliable tool integration.
Full story

Armin Ronacher discovered that newer versions of Anthropic's Claude models, particularly Opus 4.8, occasionally generate tool calls with fabricated fields in nested arrays. These invalid parameters do not match the expected schema, leading to automatic rejections by the receiving system. While the core edit operation remains correct, the mismatch forces repeated retries, disrupting automated workflows. The issue highlights a growing challenge as AI models become more capable but also more unpredictable in their interactions with external tools and APIs.

Why this matters
Developers

Developers must implement robust error handling for tool calls to account for schema mismatches.

Businesses

Companies integrating AI tools risk workflow disruptions due to unpredictable model behavior.

Everyone

AI models' increasing complexity may introduce subtle integration challenges.

Glossary
schema validation
A process that checks if data conforms to a predefined structure or format.
Sources · 1
Read next
More stories