Sign inGet started
Paper · arXiv

Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance

Tool use has become central to modern LLM agents, yet interface design is rarely isolated as an experimental variable. This paper studies whether schema based tool contracts and structured validation diagnostics improve reliability under strict interaction budgets. We evaluate three conditions that preserve identical tool semantics and information content: free form documentation, JSON Schema specifications, and JSON Schema with structured diagnostics. We implement a deterministic software engineering sandbox with logs, metrics, configurations, and repository tasks, and evaluate a fully crossed pilot with one open local model, three seeds, three interface conditions, and four budgets. We ...

AuthorsAkshey Sigdel, Rista Baral
Primary categorycs.SE
Published12 March 2026
Last updated at source12 March 2026
cs.SEcs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/c233b433-a8f6-4a72-aba3-c96ed6715492" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.