@inproceedings{tomar-nangia-2026-tools,
title = "Do Tools Matter, or Just Their Descriptions?",
author = "Tomar, Ananya and
Nangia, Ayush",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.54/",
pages = "650--666",
ISBN = "979-8-89176-466-8",
abstract = "Tool-augmented language models are increasingly applied to financial document reasoning, a setting that demands numerical precision over long financial filings. Earlier comparisons either mix up the model with its scaffolding or report tool-use gains without separating code, strategy, and environment. We isolate these factors in a controlled same-model ablation: six configurations share an identical GPT-5 backbone and differ only in the tool surface (callable tools plus their descriptions), with one control that additionally forces sub-model delegation. On DocMath-Eval under oracle context, the fully equipped configuration beats the restricted-tool baseline by +3.6 points (p=0.0028). Where this gain comes from matters more than its size: the system tools that give that configuration its name are used on under 0.2{\%} of samples, and a description-only control, which describes the same tools but never runs them, performs almost identically (within 1 point on every split). The benefit comes from the tool descriptions, not from executing the tools. On long-document splits, the equipped model uses fewer iterations, has answers available earlier when runs are cut short, and varies its tool mix with document length. Comprehension errors dominate the hardest failures: the bottleneck is document comprehension, not the tool interface."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tomar-nangia-2026-tools">
<titleInfo>
<title>Do Tools Matter, or Just Their Descriptions?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="family">Tomar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Nangia</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 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Tool-augmented language models are increasingly applied to financial document reasoning, a setting that demands numerical precision over long financial filings. Earlier comparisons either mix up the model with its scaffolding or report tool-use gains without separating code, strategy, and environment. We isolate these factors in a controlled same-model ablation: six configurations share an identical GPT-5 backbone and differ only in the tool surface (callable tools plus their descriptions), with one control that additionally forces sub-model delegation. On DocMath-Eval under oracle context, the fully equipped configuration beats the restricted-tool baseline by +3.6 points (p=0.0028). Where this gain comes from matters more than its size: the system tools that give that configuration its name are used on under 0.2% of samples, and a description-only control, which describes the same tools but never runs them, performs almost identically (within 1 point on every split). The benefit comes from the tool descriptions, not from executing the tools. On long-document splits, the equipped model uses fewer iterations, has answers available earlier when runs are cut short, and varies its tool mix with document length. Comprehension errors dominate the hardest failures: the bottleneck is document comprehension, not the tool interface.</abstract>
<identifier type="citekey">tomar-nangia-2026-tools</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.54/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>650</start>
<end>666</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Tools Matter, or Just Their Descriptions?
%A Tomar, Ananya
%A Nangia, Ayush
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F tomar-nangia-2026-tools
%X Tool-augmented language models are increasingly applied to financial document reasoning, a setting that demands numerical precision over long financial filings. Earlier comparisons either mix up the model with its scaffolding or report tool-use gains without separating code, strategy, and environment. We isolate these factors in a controlled same-model ablation: six configurations share an identical GPT-5 backbone and differ only in the tool surface (callable tools plus their descriptions), with one control that additionally forces sub-model delegation. On DocMath-Eval under oracle context, the fully equipped configuration beats the restricted-tool baseline by +3.6 points (p=0.0028). Where this gain comes from matters more than its size: the system tools that give that configuration its name are used on under 0.2% of samples, and a description-only control, which describes the same tools but never runs them, performs almost identically (within 1 point on every split). The benefit comes from the tool descriptions, not from executing the tools. On long-document splits, the equipped model uses fewer iterations, has answers available earlier when runs are cut short, and varies its tool mix with document length. Comprehension errors dominate the hardest failures: the bottleneck is document comprehension, not the tool interface.
%U https://aclanthology.org/2026.finnlp-1.54/
%P 650-666
Markdown (Informal)
[Do Tools Matter, or Just Their Descriptions?](https://aclanthology.org/2026.finnlp-1.54/) (Tomar & Nangia, FinNLP 2026)
ACL
- Ananya Tomar and Ayush Nangia. 2026. Do Tools Matter, or Just Their Descriptions?. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 650–666, Budapest, Hungary. Association for Computational Linguistics.