Dust aerosols play a pivotal role in climate, ecosystems, and human health, yet global dust emission estimates in current Earth System Models (ESMs) remain highly uncertain due to over-simplified surface parameterizations and inconsistent particle size representations. Vegetation effects on dust emissions are often inconsistently and simplistically represented across models, limiting physical realism and land-atmosphere coupling. This study bridges this gap by utilizing the vegetation cover derived from the land surface model OR-CHIDEE, and accounting for its effects on the dust emission scheme in the atmospheric model LMDzORINCA. The influence of including the very large dust particles (diameter greater than 100 & micro;m) is also studied using two representations: a single-mode dominated by fine micrometre-sized particles, and a multi-mode representation comprising four size modes covering a range exceeding 100 & micro;m. Incorporating vegetation reduces the global dust emissions by 23 %, primarily over semi-arid regions, and shifts the spatial dominance toward sparsely vegetated deserts, such as North Africa and East Asia. Including vegetation also leads to an improvement in model agreement with observations by reducing mean biases by approximately 50 %-80 % across various dust metrics, notably mitigating overestimations in dust aerosol optical depth (DAOD) over north-western India and in dust deposition over Antarctica. Furthermore, different particle size representations indicate that accurate reproduction of DAOD depends on the adequate representation of fine particles. Overall, this ESM-consistent framework, achieved by explicitly integrating vegetation effects and comprehensive particle size distributions, provides a pathway for future coupled land-atmosphere simulations under climate change.