Function-calling Schemas as De Facto Governance: Measuring Agency Reallocation through a Compiled Rule

Function-calling schemas, presented in practitioner guides as mechanisms for structured output, operate as de facto governance instruments within model–tool ecosystems. While most documentation focuses on syntactic validity and schema adherence, little attention has been paid to how parameter defaults, validators, and enforced signatures redistribute agency among the operator, the model, and the external tool. This paper introduces the Agency Reallocation Index (ARI), a quantitative measure that captures this redistribution through entropy reduction and Shapley attribution across three control dimensions: operator, model, and tool. Treating the schema as a regla compilada (a compiled rule that pre-structures permissible actions), the study demonstrates how defaults and validation layers govern results as effectively as explicit human instruction. A factorial experiment over controlled tool-calling tasks isolates the effects of validator strictness, default intensity, and signature breadth on agency allocation. The findings show that higher validator rigidity or hard defaults consistently increase tool agency while compressing model autonomy, exposing a governance gradient encoded in interface design. The paper concludes that schema architecture not only constrains model behavior but also formalize a programmable distribution of authority that should be audited alongside conventional metrics of accuracy and reliability. DOI Primary archive: https://doi.org/10.5281/zenodo.17533080 Secondary archive: https://doi.org/10.6084/m9.figshare.30541049 SSRN: Pending assignment (ETA: Q4 2025)

Related Organizations

Keywords

Artificial Intelligence/legislation & jurisprudence, Linguistics/legislation & jurisprudence, Machine ciphers, Machine sewing, Unsupervised Machine Learning/classification, Science/history, Data science, Anthropological ethics, Supervised Machine Learning/economics, Abortion, Legal/ethics, Linguistics/organization & administration, Linguistics/standards, Science/standards, Artificial Intelligence/ethics, Supervised Machine Learning/ethics, Linguistics/methods, Liability, Legal, Linguistics/education, Supervised Machine Learning/classification, Machine Learning/trends, Water science, Machine Learning/history, Allied health personnel--Professional ethics, Linguistics/legislation & jurisprudence, Embroidery, Machine, Communism and linguistics, Accounting--Professional ethics, Supervised Machine Learning, Physical science, Legal research--Automation, Science/education, Legal Services/trends, Artificial Intelligence/economics, Science, Supervised Machine Learning/trends, Unsupervised Machine Learning/history, Linguistics/ethics, Machine theory, Drum machine, Science/instrumentation, Applied science, Machine Learning/classification, Machine learning, Agreement (legal), Comparative linguistics, Artificial Intelligence/trends, Machine Learning/legislation & jurisprudence, Anaphora (Linguistics), Legal aid--Evaluation, Science/trends, Materials science, Artificial Intelligence/supply & distribution, Military Science, Human science, Cartesian linguistics, Legal text, Linguistics/statistics & numerical data, Machine Learning/ethics, Artificial intelligence, Artificial Intelligence/statistics & numerical data, Areal linguistics, Applied linguistics--Data processing, Comparative linguistics--Statistical methods, Legal aid--Auditing, Artificial Intelligence/standards, Machine Learning, Linguistics/history, Legal Guardians, Alcoholism counselors--Professional ethics, Legal profession, Archaisms (Linguistics), Machine Learning/standards, Machine shops, Linguistics/trends, Science/ethics, Legal Services/education, Legal photography--History, Behavioural science, Machine quilting, Artificial Intelligence/supply & distribution, Computational science, Machine Learning/supply & distribution, Legal regulation, Machine parts, Abortion, Legal/standards, Linguistics/classification, Linguistics/organization & administration, Analogy (Linguistics), Artificial Intelligence/statistics & numerical data, Legal Services/ethics, Unsupervised Machine Learning/ethics, Artificial Intelligence/classification, Abortion, Legal, Legal system, Christian Science, Machine Learning/supply & distribution, Causative (Linguistics), Legal remedy, Machine-to-machine communications, Machine appliqué, Machine Learning/legislation & jurisprudence, Combination (Linguistics), Machine knitting, Artificial Intelligence/history, Applied linguistics--Research, Legal advertising, Linguistics/statistics & numerical data, Artificial Intelligence, Supervised Machine Learning/standards, Science journalism, Abortion, Legal/veterinary, Categorization (Linguistics), Legal procedure, Data Science, Linguistics, Machine Learning/economics, Artificial Intelligence/legislation & jurisprudence, Ensemble learning (Machine learning), Applied linguistics--Statistical methods, Componential analysis (Linguistics), Accountants--Professional ethics, FOS: Languages and literature, Machine design, Cognitive Science, Linguistics/instrumentation, Abortion, Legal/economics, Legal Services, Competence and performance (Linguistics), Unsupervised Machine Learning

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

0

Average

Green

Related to Research communities

Knowmad Institut