Tight glutenite rservoirs characterization and effective hydrocarbon-bearing formation identification faced great challenge due to ultra-low porosity, utra-low permeability and complicated pore structure. In addition, tight glutenite reservoirs generally had no natural productive capacity, fracturing fracture-building technique always needed to improve hydrocarbon production capacity. Pore structure characterization and friability prediction were essential in improving such type of reservoir evaluation. In this study, fractured tight glutenite reservoirs in Permian Jiamuhe Formation that located in northwest margin of Junggar Basin, northwest China was chosen as an example, 25 typical core samples were drilled and simultaneously applied for mercury injection capillary pressure (MICP), nuclear magnetic resonance (NMR) and whole-rock mineral X-ray diffraction experiments. The limitation of pore structure characterization based on NMR logging was analyzed, and a novel method of synthetizing pseudo pore-throat radius (Rc) distribution from porosity frequency spectra, and used to characterize fractured formation pore structure was established, the porosity frequency spectra were extracted from electrical image logging. Based on whole-rock mineral X-ray diffraction experimental data, quartz and calcite were considered as the fragile mineral in our target formation, and rock mineral component ratio method was used to predict brittleness index (BI). The statistical model that raised by Jin et al. (2015) was used to predict two types of fracture toughness KIC and KIIC. BI, KIC and KIIC were combined to characterize tight glutenite reservoirs friability (Frac). Combining with maximal pore-throat radius (Rmax, reflected rock pore structure) and Frac, our target formations were classified into four clusters. Meanwhile, relationships among Rmax, Frac and daily hydrocarbon production per meter (DI) was analyzed, and positively relations among them was observed. Formations with good pore structure and high Frac always contained high deliverability, and vice versa. A model to predict fractured tight glutenite reservoirs DI from well logging data was established. Comparison of predicted DI with the extracted results from drill stem test (DST) data illustrated the reliability of our raised models. This would be valueable in determining optimal hydrocarbon production intervals and formulating reasonable developed plans.