@inproceedings{sharma-tapadiya-2026-tool,
title = "Do Tool Schemas Fully Specify Argument Binding?",
author = "Sharma, Jai Kumar and
Tapadiya, Peeyush",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.66/",
pages = "957--972",
ISBN = "979-8-89176-485-9",
abstract = "Tool schemas constrain the structure of a call but need not determine how request evidence becomes argument values. We formalize this layer as a field-level binding contract over presence, evidence, ordered operations, parameters, and validation, and state an identifiability boundary: no schema-only estimator can guarantee recovery of policy distinctions absent from its input. We audit all 1,311 filtered requests in pinned Berkeley Function-Calling Leaderboard (BFCL) V4 Live Simple and Multiple with five open checkpoints and the official abstract-syntax-tree (AST) checker. A partial structural diagnostic and AST acceptance are non-nested: 1,470 of 6,555 calls pass only the diagnostic and 50 pass only AST. A stratified AI-only audit finds coarse concern detection far more consistent across two isolated passes than fine attribution. A pre-specified test of a deterministic schema-derived operation-label encoding gives 67.70{\%} AST acceptance versus 68.27{\%} under the same guidance without field tags ($-0.56$ points; 95{\%} task-cluster CI $-1.17$ to $+0.05$; 186 fixes, 223 breaks). Value-only turnover is nearly balanced; the net imbalance sits in key-set changes. The point estimate reverses sign on one post-hoc out-of-panel checkpoint; thus no improvement is established on the fixed panel, and independently authored contracts remain untested."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-tapadiya-2026-tool">
<titleInfo>
<title>Do Tool Schemas Fully Specify Argument Binding?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jai</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peeyush</namePart>
<namePart type="family">Tapadiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>Tool schemas constrain the structure of a call but need not determine how request evidence becomes argument values. We formalize this layer as a field-level binding contract over presence, evidence, ordered operations, parameters, and validation, and state an identifiability boundary: no schema-only estimator can guarantee recovery of policy distinctions absent from its input. We audit all 1,311 filtered requests in pinned Berkeley Function-Calling Leaderboard (BFCL) V4 Live Simple and Multiple with five open checkpoints and the official abstract-syntax-tree (AST) checker. A partial structural diagnostic and AST acceptance are non-nested: 1,470 of 6,555 calls pass only the diagnostic and 50 pass only AST. A stratified AI-only audit finds coarse concern detection far more consistent across two isolated passes than fine attribution. A pre-specified test of a deterministic schema-derived operation-label encoding gives 67.70% AST acceptance versus 68.27% under the same guidance without field tags (-0.56 points; 95% task-cluster CI -1.17 to +0.05; 186 fixes, 223 breaks). Value-only turnover is nearly balanced; the net imbalance sits in key-set changes. The point estimate reverses sign on one post-hoc out-of-panel checkpoint; thus no improvement is established on the fixed panel, and independently authored contracts remain untested.</abstract>
<identifier type="citekey">sharma-tapadiya-2026-tool</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.66/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>957</start>
<end>972</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Tool Schemas Fully Specify Argument Binding?
%A Sharma, Jai Kumar
%A Tapadiya, Peeyush
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F sharma-tapadiya-2026-tool
%X Tool schemas constrain the structure of a call but need not determine how request evidence becomes argument values. We formalize this layer as a field-level binding contract over presence, evidence, ordered operations, parameters, and validation, and state an identifiability boundary: no schema-only estimator can guarantee recovery of policy distinctions absent from its input. We audit all 1,311 filtered requests in pinned Berkeley Function-Calling Leaderboard (BFCL) V4 Live Simple and Multiple with five open checkpoints and the official abstract-syntax-tree (AST) checker. A partial structural diagnostic and AST acceptance are non-nested: 1,470 of 6,555 calls pass only the diagnostic and 50 pass only AST. A stratified AI-only audit finds coarse concern detection far more consistent across two isolated passes than fine attribution. A pre-specified test of a deterministic schema-derived operation-label encoding gives 67.70% AST acceptance versus 68.27% under the same guidance without field tags (-0.56 points; 95% task-cluster CI -1.17 to +0.05; 186 fixes, 223 breaks). Value-only turnover is nearly balanced; the net imbalance sits in key-set changes. The point estimate reverses sign on one post-hoc out-of-panel checkpoint; thus no improvement is established on the fixed panel, and independently authored contracts remain untested.
%U https://aclanthology.org/2026.realm-1.66/
%P 957-972
Markdown (Informal)
[Do Tool Schemas Fully Specify Argument Binding?](https://aclanthology.org/2026.realm-1.66/) (Sharma & Tapadiya, REALM 2026)
ACL
- Jai Kumar Sharma and Peeyush Tapadiya. 2026. Do Tool Schemas Fully Specify Argument Binding?. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 957–972, Budapest, Hungary. Association for Computational Linguistics.