# Callability Is Not Operability: Controlled Interface Interventions for LLM Agents

arXiv: https://arxiv.org/abs/2608.23628 · HTML: https://mlsanity.com/paper/2608.23628/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 9 of 9)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents](https://mlsanity.com/paper/2506.16042/) (2025)
- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [Cordon: Semantic Transactions for Tool-Using LLM Agents](https://mlsanity.com/paper/2606.17573/) (2026)
- [CLI-Anything: Towards Agent-Native Computer Use](https://mlsanity.com/paper/2606.03854/) (2026)
- [Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures](https://mlsanity.com/paper/2608.02645/) (2026)
- [Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance](https://mlsanity.com/paper/2603.13404/) (2026)
- [Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems](https://mlsanity.com/paper/2605.10555/) (2026)

## Built on by (most cited first, 1 of 1)

- [UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents](https://mlsanity.com/paper/2610.05622/) (2026)

## Abstract (arXiv)

A tool call can be perfectly valid yet still leave an autonomous agent unable to determine what to do next. For example, if an external effect commits but its response is lost, committed and uncommitted states may become indistinguishable to the agent even though they require different continuation actions. We study this gap between callability and operability: whether a tool interface exposes the action-relevant state and semantics needed for an agent to continue safely under operational uncertainty. We operationalize tool operability through Agent-First Tooling (AFT), a set of interface mechanisms spanning selective capability discovery, execution lifecycle and recovery, explicit external-effect semantics, machine-readable results, and postcondition verification. We introduce AFT-Bench, a controlled interface-intervention framework that holds the task, backend, initial state, injected failure, agent, and language model fixed while varying the interface exposed to the agent.